Home
Learn
Feed
Ladder
Saved
← Paths
🤖
LLM & ML Engineering
From bias-variance to transformers, RAG, RLHF, and production MLOps.
Curriculum · 997 lessons
01
One Hot Encoding
intro
3m
02
Features and Labels
intro
4m
03
Descriptive Statistics Mean Median Mode
intro
4m
04
Pooling Layers
intro
4m
05
Linear Regression
intro
5m
06
What Is Supervised Learning
intro
4m
07
The Bag of Words Model
intro
4m
08
Image Representation and Channels
intro
4m
09
Time Series Components Trend And Seasonality
intro
4m
10
The Sources of Bias in Data
intro
4m
11
Zero Shot Prompting
intro
4m
12
The Perceptron and Activation
intro
4m
13
The Multi Step Tool Use
intro
4m
14
Tokenization Overview
intro
4m
15
The Language Detection
intro
4m
16
Feature Scaling
intro
3m
17
Word Embeddings
intro
4m
18
Accuracy And Its Pitfalls
intro
4m
19
Model Serving Architectures
intro
4m
20
The ML Project Lifecycle
intro
4m
21
The Cost Function Intuition
intro
4m
22
Decision Tree Splitting Criteria
intro
4m
23
The Markov Decision Process
intro
4m
24
K Means Clustering Revisited
intro
4m
25
The Recommendation Problem
intro
4m
26
The ML Pipeline Stages
intro
4m
27
Embedding Space Geometry
intro
4m
28
The Confusion Matrix
intro
4m
29
Feature Engineering Overview
intro
4m
30
Overfitting And Underfitting
intro
4m
31
Generative Versus Discriminative Models
intro
4m
32
The KV Cache in Transformers
intro
4m
33
The Linear Regression
intro
4m
34
The Recommendation Funnel
intro
4m
35
The Pretraining Objective
intro
4m
36
The Feature Store Online Offline
intro
4m
37
The ML System Design Framework
intro
5m
38
The Accuracy Paradox
intro
4m
39
The Multilayer Perceptron
intro
4m
40
The Gradient Descent Intuition
intro
4m
41
The Problem Definition and Scoping
intro
4m
42
The Data Parallelism Training
intro
4m
43
The Full Fine Tuning
intro
4m
44
The Linear Regression Assumptions
intro
4m
45
The Model Performance Monitoring
intro
4m
46
The Markov Decision Process Deep Dive
intro
5m
47
The Word Embeddings Recap
intro
4m
48
The RAG Architecture Deep
intro
5m
49
The Prompt Structure Anatomy
intro
4m
50
The Convolution Arithmetic
intro
4m
51
The Part Of Speech Tagging Deep
intro
4m
52
Agent Architecture Deep Dive
intro
4m
53
The Feature Store
intro
4m
54
Data Parallel Training
intro
5m
55
Train Validation Test Split Revisited
intro
4m
56
The LLM Benchmark Suites
intro
5m
57
The GPU Architecture for ML
intro
4m
58
What Is Unsupervised Learning
intro
4m
59
Gradient Descent
intro
4m
60
The Adam Optimizer
intro
4m
61
Convolutional Neural Networks
intro
5m
62
Prompt Injection and Defenses
intro
5m
63
Data Collection and Labeling
intro
4m
64
The LLM Agent Loop
intro
4m
65
States Actions and Rewards
intro
4m
66
The Elbow Method
intro
3m
67
Content Based Filtering
intro
4m
68
Experiment Tracking
intro
4m
69
The Transformer Block Structure
intro
4m
70
Sampling Bias
intro
4m
71
Few Shot Prompting
intro
4m
72
The Forward Pass
intro
4m
73
Handling Missing Values
intro
4m
74
The Bias Variance Tradeoff Revisited
intro
4m
75
The Candidate Retrieval Stage
intro
4m
76
The Supervised Fine Tuning
intro
4m
77
Problem Framing and Metrics
intro
4m
78
The Pooling and Stride Recap
intro
3m
79
The Baseline Model First
intro
4m
80
The Model Parallelism
intro
4m
81
The Weight Initialization Deep
intro
4m
82
The Self Attention Deep
intro
5m
83
The System Prompt Design
intro
4m
84
The Scaling Laws Deep
intro
5m
85
The Named Entity Recognition Deep
intro
4m
86
The Collaborative Filtering Deep
intro
4m
87
The Model Registry
intro
4m
88
Logistic Regression
intro
5m
89
The Precision Recall Tradeoff
intro
4m
90
TF IDF Weighting
intro
4m
91
The Convolution Operation
intro
4m
92
Stationarity And Differencing
intro
4m
93
Precision and Recall Revisited
intro
4m
94
Variance and Standard Deviation
intro
4m
95
Byte Pair Encoding
intro
5m
96
The Tensor Cores
intro
4m
97
Loss Functions
intro
4m
98
Byte Pair Encoding Tokenization
intro
4m
99
SGD with Momentum
intro
4m
100
Few Shot In Context Learning
intro
4m
101
Stratified Sampling
intro
4m
102
REST Versus gRPC For Inference
intro
4m
103
Gini Impurity and Entropy
intro
4m
104
The Exploration Exploitation Tradeoff
intro
4m
105
The Model Registry Revisited
intro
4m
106
Cosine vs Euclidean Distance
intro
4m
107
Output Formatting Instructions
intro
4m
108
The Train Validation Test Split
intro
3m
109
The Autoencoder Revisited
intro
4m
110
Quantization to Int8 and Int4
intro
5m
111
The Logistic Regression
intro
4m
112
The Reward Model Training
intro
5m
113
The Stratified Sampling
intro
4m
114
R Squared and Adjusted R Squared
intro
4m
115
The Convolutional Layer Recap
intro
4m
116
The Stochastic Gradient Descent
intro
4m
117
The Mini Batch Gradient Descent
intro
4m
118
The Checkpoint and Resume Training
intro
4m
119
The Agent Memory Architectures
intro
5m
120
The Instruction Tuning
intro
4m
121
The Polynomial Regression
intro
4m
122
The Activation Function Choice
intro
4m
123
The Data Drift Detection Deep
intro
5m
124
The Bellman Optimality Equation
intro
5m
125
The Sentence Embeddings
intro
4m
126
The Embedding Visualization
intro
5m
127
The Scaled Dot Product
intro
4m
128
The Chunking Strategies Deep
intro
5m
129
The Receptive Field Calculation
intro
4m
130
The Compute Optimal Training
intro
5m
131
Episodic vs Semantic Memory
intro
4m
132
Offline vs Online Evaluation
intro
4m
133
Model Parallel Training
intro
5m
134
The F1 And F Beta Score
intro
4m
135
Tool Calling and Function Schemas
intro
4m
136
Filters and Feature Maps
intro
4m
137
Scaled Dot Product Attention
intro
5m
138
Label Bias
intro
4m
139
Backpropagation Intuition
intro
4m
140
Probability Distributions Overview
intro
4m
141
The Perplexity Revisited
intro
5m
142
The Chinchilla Optimal
intro
5m
143
Temperature and Sampling
intro
4m
144
The LLM as a Judge Pattern
intro
5m
145
Feature Engineering Basics
intro
5m
146
Dynamic Batching For Throughput
intro
4m
147
What Is Reinforcement Learning
intro
5m
148
N Gram Language Models
intro
4m
149
Dataset Versioning
intro
4m
150
The Learning Rate Schedule
intro
4m
151
Naive Bayes Assumptions
intro
4m
152
The Policy and Value Function
intro
4m
153
Hierarchical Clustering
intro
4m
154
Autocorrelation And The ACF
intro
4m
155
Collaborative Filtering User Based
intro
4m
156
The Query Key Value Projections
intro
4m
157
Sentiment Analysis Pipeline
intro
4m
158
GPTQ and AWQ Quantization
intro
5m
159
The K Nearest Neighbors
intro
4m
160
The Freshness and Recency
intro
5m
161
The Point In Time Correctness
intro
5m
162
The Data Collection Strategy
intro
5m
163
Regression Metrics MAE MSE RMSE MAPE
intro
5m
164
The Error Analysis Workflow
intro
4m
165
The Human Evaluation Protocols
intro
5m
166
The WordPiece Tokenizer
intro
4m
167
The Memory Bandwidth Bound
intro
4m
168
The Prediction Distribution Shift
intro
4m
169
The Value Iteration Algorithm
intro
5m
170
The Multi Head Attention Deep
intro
5m
171
The Few Shot Example Selection
intro
5m
172
The Image Augmentation Strategies
intro
4m
173
The Matrix Factorization ALS
intro
4m
174
Human in the Loop Deep Dive
intro
4m
175
The Maximum Likelihood Principle
intro
5m
176
The ReAct Reasoning Pattern
intro
4m
177
The Approximate Nearest Neighbor Problem
intro
4m
178
The Diffusion Model Forward Process
intro
5m
179
The Tool Result Grounding
intro
4m
180
The Few Shot In Context Learning
intro
4m
181
The Ridge And Lasso Recap
intro
4m
182
The Normalization Layers Compared
intro
5m
183
The Chunk Overlap Tuning
intro
5m
184
Reading The Confusion Matrix
intro
4m
185
The F1 Score
intro
3m
186
Label Preserving Data Augmentation
intro
4m
187
ReLU And Its Variants
intro
4m
188
Dot Product Versus Cosine Similarity
core
4m
189
The Logistic Regression Classifier
core
5m
190
The ONNX Interchange Format
core
5m
191
K Nearest Neighbors
core
5m
192
The Spell Correction NLP
core
4m
193
Grid Search Versus Random Search
core
4m
194
Chain of Thought Prompting
core
4m
195
Gradient Accumulation
core
4m
196
Epsilon Greedy and Softmax
core
4m
197
The Moving Average Smoothing
core
4m
198
The Overlap in Chunking
core
4m
199
Binning and Discretization
core
4m
200
The Gradient Accumulation
core
4m
201
The KNN Weighting Schemes
core
4m
202
The Model Checkpointing
core
4m
203
The Attention Masks Types
core
5m
204
The Negative Instructions
core
4m
205
The Keyword Extraction
core
4m
206
Precision and Recall
core
4m
207
Document Chunking Strategies
core
5m
208
Naive Bayes
core
5m
209
Sentiment Analysis
core
4m
210
Gaussian Naive Bayes
core
4m
211
Padding and Stride
core
4m
212
The Silhouette Score
core
4m
213
Forecasting Evaluation Metrics
core
4m
214
The Embedding And Unembedding
core
4m
215
The Chunking Strategy for Documents
core
5m
216
Hyperparameter Tuning Grid Search
core
4m
217
The Normal Distribution
core
4m
218
The Decision Boundary Visualization
core
4m
219
The Toxicity Detection
core
5m
220
The Data Sampling Strategies
core
4m
221
The Naive Bayes Variants
core
4m
222
The Delimiters And Structure
core
4m
223
The Sentiment Analysis Deep
core
4m
224
Decision Trees
core
5m
225
Data Augmentation
core
4m
226
Batch vs Real Time Inference
core
4m
227
The Encoder Decoder Architecture
core
5m
228
Structured Output and JSON Mode
core
5m
229
Hyperparameter Search Strategies
core
6m
230
The Confusion Matrix And F1 Score
core
5m
231
The Confusion Matrix In Depth
core
5m
232
Caching Model Responses
core
4m
233
Part Of Speech Tagging
core
4m
234
Pruning Decision Trees
core
4m
235
Pooling Layers Revisited
core
4m
236
Lag Features For ML Forecasting
core
4m
237
The Causal Attention Mask
core
4m
238
The Recall vs Latency Tradeoff
core
4m
239
Text Classification Basics
core
5m
240
Datetime Feature Extraction
core
5m
241
Cross Validation K Fold
core
4m
242
The Bernoulli and Binomial
core
4m
243
The Sigmoid And Decision Boundary
core
4m
244
The Content Filtering and Moderation
core
5m
245
The Data Augmentation Strategies
core
4m
246
Ranking Metrics and MRR
core
4m
247
The Activation Functions ReLU GELU
core
4m
248
The Learning Rate Scaling Rule
core
4m
249
The Rubric Based Scoring
core
5m
250
The Human In The Loop Gates
core
4m
251
Out of Vocabulary Handling
core
4m
252
The Batch Size and GPU Utilization
core
4m
253
The Parameter Efficient Fine Tuning
core
5m
254
The Decision Tree Pruning Recap
core
4m
255
The Early Stopping Patience
core
4m
256
The Feature Drift Monitoring
core
4m
257
The Policy Iteration Algorithm
core
5m
258
The Role And Persona Prompting
core
4m
259
The Text Classification Deep
core
4m
260
Cross Validation
core
5m
261
Transfer Learning
core
4m
262
Shadow Deployment of Models
core
4m
263
Mean Squared Error And MAE
core
4m
264
GPU Versus CPU Inference Tradeoffs
core
4m
265
The Bias Term
core
4m
266
Subword Tokenization Revisited
core
4m
267
Data Augmentation for Images
core
5m
268
Prompt Templates and Versioning
core
4m
269
Monte Carlo Methods
core
4m
270
Intersection over Union
core
4m
271
DBSCAN Density Clustering
core
5m
272
Item Based Collaborative Filtering
core
5m
273
Reproducible Training Runs
core
5m
274
Model Interpretability Importance
core
4m
275
Mean Absolute Error vs RMSE
core
4m
276
TF IDF Vectorization
core
5m
277
Feature Scaling Normalization and Standardization
core
5m
278
Model Pruning for LLMs
core
5m
279
The Feature Freshness
core
4m
280
The Recurrent Network Recap
core
4m
281
The Learning Rate Effects
core
5m
282
The Loss Functions Overview
core
5m
283
The Gradient Clipping Recap
core
4m
284
The Mixed Precision Training
core
5m
285
The Agent Orchestration Frameworks
core
5m
286
The Softmax Regression
core
4m
287
The Dropout Variants
core
4m
288
The Alerting Thresholds Ml
core
4m
289
The Contrastive Learning
core
5m
290
The Siamese Networks
core
5m
291
The Cosine Similarity Deep Dive
core
5m
292
The Embedding Normalization
core
4m
293
The Depthwise Separable Convolution
core
5m
294
K Means Clustering
core
4m
295
Learning Rate Warmup
core
4m
296
Recurrent Neural Networks
core
5m
297
Output Guardrails and Validation
core
5m
298
K Fold Cross Validation
core
5m
299
R Squared For Regression
core
4m
300
Text Classification Pipelines
core
5m
301
The Feature Pipeline
core
5m
302
Feature Importance from Trees
core
4m
303
Data Augmentation for Vision
core
4m
304
Exponential Smoothing
core
4m
305
Implicit vs Explicit Feedback
core
5m
306
Multi Head Attention Revisited
core
5m
307
The IVF Inverted File Index
core
5m
308
The Role And System Prompt
core
5m
309
Gradient Descent Variants
core
5m
310
Text Feature Extraction
core
5m
311
The L2 Ridge Regularization
core
4m
312
Ensemble Methods Overview
core
4m
313
Correlation vs Causation
core
4m
314
The Distance Metrics
core
4m
315
The Hallucination Causes
core
5m
316
The Dataset Versioning
core
4m
317
Batch versus Real Time Inference
core
5m
318
The F Beta Weighting
core
4m
319
The Parallel Tool Execution
core
4m
320
Token Cost and Pricing
core
4m
321
The Compute Bound Kernels
core
4m
322
The Learning Rate Finder
core
4m
323
The Cross Attention Deep
core
5m
324
The Prompt Decomposition
core
5m
325
The Non Max Suppression Deep
core
5m
326
The Sparse Activation
core
5m
327
The Text Summarization Extractive
core
4m
328
Function Schema Design
core
5m
329
Canary Model Rollout
core
4m
330
Constitutional AI and Self Critique
core
5m
331
Feature Importance
core
5m
332
Encoding Categorical Variables
core
5m
333
Named Entity Recognition
core
5m
334
Dropout as Regularization
core
4m
335
The Streaming Token Interface
core
4m
336
The Sliding Window For Sequences
core
4m
337
Metadata Filtering in Vector Search
core
5m
338
The Role Specialization Agents
core
5m
339
Context Length and Tokens
core
4m
340
The CPU vs GPU vs TPU
core
5m
341
The Prefix and Prompt Tuning
core
5m
342
The Distillation For Efficiency
core
5m
343
L1 and L2 Regularization
core
5m
344
Perplexity
core
4m
345
Gradient Clipping
core
4m
346
Data Drift and Concept Drift
core
5m
347
Top K and Top P Sampling
core
5m
348
Evaluation Harnesses for LLMs
core
6m
349
Mixed Precision Training
core
5m
350
Handling Missing Data
core
5m
351
Content Based Recommendation
core
5m
352
The ROC Curve And AUC
core
5m
353
The KV Cache For Transformers Revisited
core
5m
354
The Training Loop
core
5m
355
Word2vec Skip Gram
core
5m
356
Sampling Techniques
core
5m
357
Convex versus Non Convex Optimization
core
4m
358
Planning and Decomposition
core
5m
359
The Learning Rate in Boosting
core
4m
360
The Bellman Equation
core
5m
361
The Receptive Field
core
5m
362
Principal Component Analysis Revisited
core
5m
363
The Prophet Model
core
4m
364
The Feature Store Revisited
core
5m
365
The Feed Forward Network
core
4m
366
The Fairness Definitions Overview
core
5m
367
The HNSW Graph Index
core
5m
368
Chain Of Thought Revisited
core
5m
369
Dropout Regularization
core
4m
370
Imputation Strategies
core
5m
371
The L1 Lasso Regularization
core
4m
372
Random Search Tuning
core
4m
373
The Hypothesis Testing Framework
core
5m
374
The Ordinary Least Squares
core
5m
375
The Ranking Stage
core
5m
376
The Red Teaming of LLMs
core
5m
377
The Data Labeling Pipeline
core
5m
378
Offline and Online Evaluation
core
5m
379
The Embedding Layers
core
4m
380
The Data Centric vs Model Centric
core
5m
381
The Pipeline Parallelism
core
5m
382
The Synchronous SGD
core
4m
383
The Pairwise Comparison Eval
core
6m
384
The Hierarchical Planning Agents
core
5m
385
The SentencePiece Unigram Model
core
5m
386
The ONNX Runtime
core
4m
387
The Domain Adaptation
core
5m
388
The Logistic Regression Deep
core
5m
389
The Data Augmentation Images
core
4m
390
The Concept Drift Detection
core
5m
391
The Temporal Difference Learning Deep Dive
core
6m
392
The Sliding Window Attention
core
5m
393
The Query Rewriting For RAG
core
5m
394
The Chain Of Thought Prompting Deep
core
5m
395
The Anchor Boxes
core
5m
396
The Mixture Of Experts Deep
core
6m
397
The Question Answering Extractive
core
4m
398
The Bayesian Personalized Ranking
core
4m
399
Planning and Reasoning Deep Dive
core
5m
400
Label Smoothing
core
4m
401
Model Monitoring in Production
core
5m
402
Autoencoders
core
5m
403
Bagging Versus Boosting
core
6m
404
Seasonality And Trend Decomposition
core
5m
405
The Brier Score
core
4m
406
Normalization and Standardization
core
5m
407
Data Validation and Schemas
core
5m
408
Weight Initialization Strategies
core
4m
409
The Cold Start Problem Revisited
core
5m
410
The T Test
core
4m
411
The Threshold Tuning
core
4m
412
The Grounding and Citation
core
5m
413
The Retraining Cadence
core
5m
414
The Reproducibility Seeds
core
5m
415
The Instruction Following Eval
core
5m
416
The Cost Control In Agent Loops
core
5m
417
The GPU Memory Hierarchy
core
5m
418
The Adapter Layers
core
5m
419
The Shadow Deployment Ml
core
4m
420
The Activation Recomputation
core
5m
421
The Session Based Recommendation
core
4m
422
AdaGrad And Adaptive Gradients
core
4m
423
Bias, variance & overfitting
core
6m
424
Positional Encoding
core
4m
425
Vanishing and Exploding Gradients
core
5m
426
Tool Use And Function Calling
core
5m
427
Reranking Retrieved Results
core
5m
428
The Curse of Dimensionality
core
5m
429
Outlier Detection
core
5m
430
The Precision Recall Curve
core
5m
431
Quantization For Inference Int8
core
5m
432
Autoscaling Inference Services
core
5m
433
Learning Rate Intuition
core
4m
434
Online vs Offline Features
core
5m
435
Momentum and Nesterov
core
4m
436
Memory for Agents Short and Long Term
core
5m
437
Random Forests and Bagging
core
5m
438
Dynamic Programming for RL
core
5m
439
Classic CNN Architectures
core
5m
440
Node Classification
core
5m
441
Data Versioning With DVC
core
5m
442
Positional Encodings Sinusoidal
core
5m
443
Demographic Parity
core
4m
444
Vector Database Architecture
core
5m
445
The Context Window Budgeting
core
5m
446
The R Squared Metric
core
5m
447
Exploding Gradients and Clipping
core
4m
448
Outlier Detection and Treatment
core
5m
449
Log and Power Transforms
core
5m
450
The Learning Curve Diagnosis
core
4m
451
LoRA Fine Tuning
core
5m
452
Throughput versus Latency in Serving
core
4m
453
The Poisson Distribution
core
4m
454
The Confidence Intervals
core
5m
455
The Gradient Descent For Regression
core
5m
456
The Re ranking and Diversity
core
5m
457
The RLHF Pipeline
core
6m
458
Model Selection for Production
core
5m
459
ROC AUC Interpretation
core
5m
460
The Encoder Decoder
core
4m
461
The Convexity And Local Minima
core
5m
462
The Iterative Improvement Loop
core
5m
463
The Parameter Server Architecture
core
5m
464
The LLM as a Judge
core
6m
465
The Reflection And Self Critique
core
5m
466
Vocabulary Size Tradeoffs
core
5m
467
The Curriculum Learning
core
5m
468
The Random Forest Tuning
core
5m
469
The Label Smoothing
core
4m
470
The Canary Model Rollout
core
4m
471
The Labeling For Retraining
core
5m
472
The Triplet Loss
core
5m
473
The Dot Product Versus Cosine
core
4m
474
The Dimensionality of Embeddings
core
5m
475
The Multi Query Attention
core
4m
476
The Semantic Chunking
core
5m
477
The Least To Most Prompting
core
5m
478
The ResNet Skip Connections
core
5m
479
The Model Parallelism Deep
core
6m
480
The Dependency Parsing
core
5m
481
The Neural Collaborative Filtering
core
4m
482
The ReAct Pattern Deep Dive
core
5m
483
Residual Connections
core
4m
484
The Training Serving Skew
core
5m
485
GRU Cells
core
5m
486
Automatic Speech Recognition
core
5m
487
Gradient Checkpointing
core
5m
488
Time Series Forecasting Basics
core
5m
489
Calibration Curves
core
5m
490
Overfitting and Underfitting Revisited
core
5m
491
GloVe Embeddings
core
5m
492
L1 versus L2 Regularization Effects
core
4m
493
The Cost and Latency of Agent Loops
core
5m
494
Bayesian Inference Basics
core
4m
495
Transfer Learning for Images
core
5m
496
Anomaly Detection With Isolation Forest
core
5m
497
Walk Forward Validation
core
4m
498
Embeddings for Recommendations
core
5m
499
Encoder Only Versus Decoder Only Versus Encoder Decoder
core
5m
500
Bias Mitigation Preprocessing
core
5m
501
Prompt Chaining
core
5m
502
The Autoregressive Generation
core
5m
503
The P Value and Significance
core
5m
504
The Multiclass Strategies One Vs Rest
core
5m
505
The Online Learning for Recsys
core
5m
506
Fallback and Graceful Degradation
core
5m
507
Business Metric Alignment
core
5m
508
The Residual Connections
core
4m
509
The Underfitting Diagnosis
core
5m
510
The Experiment Tracking Discipline
core
5m
511
The Code Generation Eval
core
6m
512
The Agent Error Recovery
core
5m
513
The Model Quantization for Inference
core
5m
514
The Catastrophic Forgetting
core
5m
515
The Data Augmentation Text
core
4m
516
The Model Rollback Triggers
core
4m
517
The REINFORCE Policy Gradient
core
6m
518
The Multi Query Retrieval
core
5m
519
The Format Constraints And Schemas
core
5m
520
The Semantic Segmentation UNet
core
5m
521
The Quantization Aware Training
core
5m
522
The Cold Start Strategies Deep
core
4m
523
Agent Communication Protocols
core
5m
524
ROC and AUC
core
4m
525
Fine Tuning
core
5m
526
Layer Normalization
core
4m
527
A B Testing Models Online
core
5m
528
Hybrid Search Dense Plus Sparse
core
6m
529
Support Vector Machines
core
6m
530
Hyperparameter Cross Validation
core
6m
531
Collaborative Filtering
core
5m
532
Log Loss And Cross Entropy
core
5m
533
Model Sharding Across GPUs
core
5m
534
Handling Imbalanced Classes
core
5m
535
The Chain Rule in Backprop
core
5m
536
RMSProp
core
4m
537
The Vector Database for Memory
core
5m
538
Partial Dependence Plots
core
4m
539
Temporal Difference Learning
core
5m
540
Gaussian Mixture Clustering
core
5m
541
The ARIMA Model
core
5m
542
Matrix Factorization
core
5m
543
Continuous Training Pipelines
core
5m
544
Residual And Layer Norm Placement
core
5m
545
Equal Opportunity
core
4m
546
Hybrid Search Fusion
core
5m
547
The CBOW Model
core
4m
548
Polynomial and Interaction Features
core
5m
549
The Variational Autoencoder
core
5m
550
The Central Limit Theorem
core
5m
551
The Embedding Based Retrieval
core
5m
552
The Constitutional AI
core
6m
553
The Active Learning Loop
core
5m
554
The Latency Budget for Inference
core
5m
555
Macro Micro and Weighted Averaging
core
5m
556
The LSTM and GRU Recap
core
5m
557
The Feature Importance Analysis
core
5m
558
The All Reduce Collective
core
4m
559
The Factuality and Hallucination Eval
core
6m
560
Special Tokens and Chat Templates
core
5m
561
The Data Mixture for Tuning
core
5m
562
The Isotonic Regression
core
4m
563
The Outlier Detection In Production
core
5m
564
The Q Learning Convergence Conditions
core
6m
565
The Grouped Query Attention
core
5m
566
The Parent Document Retrieval
core
5m
567
The Self Consistency Deep
core
5m
568
The EfficientNet Scaling
core
5m
569
The Expert Routing Balancing
core
6m
570
The Wide And Deep Model
core
4m
571
Tool Calling Protocol Deep Dive
core
5m
572
Embedding Similarity Search
core
5m
573
Handling Class Imbalance
core
5m
574
Sequence to Sequence Models
core
5m
575
Post Training Quantization
core
5m
576
Anomaly Detection Methods
core
5m
577
Multiclass Averaging Macro Vs Micro
core
5m
578
Embedding Caches And Vector Stores
core
5m
579
The Loss Landscape
core
5m
580
The Encoder Decoder For Translation
core
5m
581
Data Augmentation for Text
core
5m
582
Warmup and Cosine Decay
core
4m
583
Structured Output Parsing
core
5m
584
SARSA
core
4m
585
Residual Networks
core
5m
586
Graph Neural Networks Intro
core
5m
587
Post Processing Calibration
core
5m
588
The Log Loss Metric
core
5m
589
The Vanishing Gradient Problem
core
5m
590
The Sequence Labeling Task
core
5m
591
The Elastic Net
core
4m
592
The Chi Squared Test
core
4m
593
The Class Imbalance Handling
core
5m
594
The Feature Crossing for Ranking
core
5m
595
Coverage and Diversity Metrics
core
5m
596
The Overfitting Diagnosis
core
5m
597
The Asynchronous SGD
core
4m
598
The Safety and Toxicity Eval
core
6m
599
The Agent Evaluation Harness
core
5m
600
The Tokenizer Training
core
5m
601
The Pruning and Sparsity
core
5m
602
The LoRA Adapters Deep
core
5m
603
The Ab Test For Models
core
5m
604
The Context Window Packing
core
5m
605
The Prompt Chaining Patterns
core
5m
606
The Object Detection YOLO
core
5m
607
The Coreference Resolution
core
5m
608
The Sequential Recommendation
core
4m
609
Agent Memory Systems Deep Dive
core
5m
610
The RMSProp Optimizer
core
4m
611
Fairness and Bias Metrics
core
5m
612
Fully Sharded Data Parallel
core
6m
613
Target Encoding
core
5m
614
Batch Normalization Revisited
core
5m
615
t SNE for Visualization
core
5m
616
Model Packaging With Containers
core
5m
617
The Cross Attention
core
5m
618
Retrieval Augmented Prompting
core
6m
619
The Exploration in Recommendations
core
5m
620
The Negative Sampling
core
5m
621
Proxy Metric Pitfalls
core
5m
622
The Reasoning Benchmarks
core
6m
623
The INT8 Calibration
core
5m
624
The Double Q Learning Trick
core
5m
625
The Citation And Attribution
core
5m
626
The Sequence Parallelism
core
5m
627
The Candidate Generation Deep
core
4m
628
Agent Guardrails Deep Dive
core
5m
629
Softening Targets With Label Smoothing
core
4m
630
Context Window and Long Context
core
5m
631
LSTM Cells
core
6m
632
Vector Indexing with HNSW
core
6m
633
AdaBoost
core
5m
634
Speculative Decoding For Latency
core
5m
635
The Validation Curve
core
5m
636
Vanishing and Exploding Gradients Revisited
core
5m
637
Context Window Management
core
5m
638
The Beta Binomial Conjugate Prior
core
4m
639
Q Learning
core
5m
640
Batch Norm in CNNs
core
5m
641
SARIMA Seasonal ARIMA
core
5m
642
Candidate Generation and Ranking
core
5m
643
Equalized Odds
core
5m
644
Product Quantization
core
5m
645
Self Consistency Decoding
core
5m
646
The Bootstrap Confidence Interval
core
5m
647
Feature Selection Methods
core
5m
648
The Reparameterization Trick
core
4m
649
QLoRA
core
5m
650
The Regularized Regression
core
5m
651
The Learning to Rank
core
6m
652
The DPO Direct Preference Optimization
core
6m
653
The Weak Supervision
core
5m
654
Model Serving Infrastructure
core
6m
655
PR AUC for Imbalanced Data
core
5m
656
The BERT Architecture
core
5m
657
The Saddle Points
core
5m
658
The Lagrange Multipliers
core
5m
659
The Constrained Optimization
core
5m
660
The Warmup And Cosine Schedule
core
5m
661
The Bias Evaluation
core
6m
662
Subword Regularization
core
5m
663
The Continual Learning
core
5m
664
The Gradient Boosting Deep
core
5m
665
The Mixup And Cutmix
core
4m
666
The Cross Encoder Versus Bi Encoder
core
6m
667
The Image Embeddings With CLIP
core
6m
668
The Sparse Attention Patterns
core
5m
669
The Hypothetical Document Embeddings
core
5m
670
The Feature Pyramid Network
core
5m
671
The DeepFM
core
5m
672
Reflexion and Self Improvement
core
5m
673
Retrieval Augmented Generation
core
5m
674
Inference Batching and Throughput
core
6m
675
Prompt Caching
core
5m
676
Synthetic Data Generation
core
5m
677
Adam and AdamW
core
5m
678
UMAP for Visualization
core
5m
679
The Inference Server
core
5m
680
Tool Use Prompting
core
6m
681
The Calibration Curve
core
5m
682
Mode Collapse In GANs
core
4m
683
The Multi Armed Bandit for Ranking
core
5m
684
AB Testing ML Models
core
6m
685
The Gradient Compression
core
4m
686
Multilingual Tokenization
core
5m
687
The Kernel Fusion
core
5m
688
The Dueling DQN Architecture
core
5m
689
The Zero Optimizer Stages
core
6m
690
Principal Component Analysis
core
5m
691
Distributed All Reduce
core
6m
692
The Singular Value Decomposition
core
5m
693
The Two Tower Model
core
5m
694
The Fairness Accuracy Tradeoff
core
5m
695
Statistical Significance in AB Tests
core
5m
696
The Latent Diffusion
core
5m
697
The Recommendation Evaluation
core
6m
698
The Jailbreak and Prompt Injection Defense
core
6m
699
The Synthetic Data Generation
core
5m
700
Feature Pipeline Design
core
6m
701
The GPT Architecture
core
5m
702
The Operator Scheduling
core
5m
703
The One Cycle Policy
core
4m
704
The Reciprocal Rank Fusion
core
5m
705
The Object Detection Faster RCNN
core
5m
706
The Two Tower Retrieval Deep
core
5m
707
Cost and Latency Optimization for Agents
core
5m
708
Nucleus Sampling
core
4m
709
Multi Head Attention
core
5m
710
The Sigmoid and Softmax Functions
core
5m
711
Attention In Seq2seq
core
5m
712
Point in Time Correctness
core
5m
713
Evaluation of Agent Trajectories
core
5m
714
Gradient Boosted Trees
core
5m
715
The Experience Replay Buffer
core
4m
716
AB Testing In Production
core
5m
717
Rotary Position Embeddings
core
5m
718
Prompt Injection Defense Revisited
core
6m
719
The Mean Average Precision
core
5m
720
The Diffusion Reverse Denoising
core
5m
721
Continuous Batching
core
5m
722
The Support Vector Machine
core
5m
723
Monitoring and Alerting for ML
core
6m
724
The Attention Recap
core
5m
725
The Data Leakage Hunting
core
6m
726
The Prioritized Experience Replay
core
6m
727
The Alibi Position Bias
core
5m
728
The Text Summarization Abstractive
core
5m
729
Sinusoidal Positional Encoding
core
5m
730
In Processing Fairness Constraints
core
5m
731
The ROUGE Score
core
5m
732
Evaluation Of Generative Models
core
5m
733
The RLHF vs DPO Comparison
core
6m
734
The Advantage Actor Critic Method
core
6m
735
The Transformer Architecture
core
6m
736
Autoencoders for Dimensionality
core
5m
737
Shadow Mode Evaluation
core
5m
738
The React Loop Revisited
core
6m
739
The RNN for Sequences
core
5m
740
Normalizing Flows
core
5m
741
Flash Attention
core
5m
742
The Transformer Recap
core
6m
743
The Expectation Maximization Recap
core
5m
744
The Cross Validation Pitfalls
core
6m
745
The Gaussian Processes
core
5m
746
The Rainbow DQN Combination
core
6m
747
The Kv Cache Optimization Deep
core
6m
748
The Cross Encoder Reranking Deep
core
5m
749
The Graph Based Recsys
core
5m
750
In Context Learning From Prompts
core
5m
751
The Autoencoder Bottleneck
core
5m
752
Model Rollback Strategies
core
5m
753
The Long Context Techniques
core
6m
754
Xavier And He Initialization
core
5m
755
Chain Of Thought Reasoning
core
4m
756
Stacked Generalization
advanced
5m
757
Masked Language Modeling
advanced
5m
758
Pretext Tasks And Self Supervision
advanced
5m
759
Bayesian Hyperparameter Optimization
advanced
5m
760
Model Versioning and Reproducibility
advanced
5m
761
Object Detection Basics
advanced
5m
762
Self Attention
advanced
5m
763
Beam Search
advanced
5m
764
Active Learning
advanced
5m
765
Multimodal Models
advanced
5m
766
Model Pruning
advanced
5m
767
The Kernel Trick
advanced
5m
768
SGD Versus Minibatch
advanced
5m
769
The Cold Start Of Model Loading
advanced
4m
770
Early Stopping
advanced
4m
771
Sequence Labeling With CRFs
advanced
5m
772
The Cosine Similarity For Text
advanced
4m
773
Hidden Markov Models
advanced
5m
774
The One Class SVM
advanced
5m
775
Anomaly Detection In Time Series
advanced
5m
776
The Right To Explanation
advanced
5m
777
The GRU Cell
advanced
5m
778
Bagging Vs Boosting
advanced
5m
779
The Generator And Discriminator
advanced
5m
780
The Model Cards and Transparency
advanced
5m
781
The Cost Monitoring Inference
advanced
4m
782
The Attention Sinks
advanced
5m
783
The Text Similarity Metrics
advanced
5m
784
Random Forests
advanced
5m
785
The Parameter Server Pattern
advanced
5m
786
The Mixture of Experts
advanced
5m
787
The Tensor Parallelism
advanced
5m
788
The Gradient Accumulation Practical
advanced
4m
789
The Adversarial Generator And Discriminator
advanced
6m
790
Model Calibration
advanced
5m
791
Explainability with LIME
advanced
5m
792
Vision Transformers
advanced
6m
793
Embeddings For Categorical Features
advanced
6m
794
The Epoch Batch and Iteration
advanced
5m
795
Retrieval Chunking for Agents
advanced
5m
796
Non Max Suppression
advanced
5m
797
The Holt Winters Method
advanced
5m
798
Weight Tying
advanced
5m
799
The LLM Evaluation Rubric
advanced
6m
800
The No Free Lunch Theorem
advanced
4m
801
The Bayes Theorem
advanced
5m
802
Calibration and the Brier Score
advanced
5m
803
The Model Debugging Techniques
advanced
5m
804
The Long Context Eval
advanced
6m
805
The Multi Agent Debate
advanced
5m
806
The Embedding Lookup
advanced
4m
807
The Synthetic Data for Tuning
advanced
6m
808
The Slo For Ml Services
advanced
5m
809
The Linear Attention
advanced
6m
810
The Topic Modeling LDA
advanced
5m
811
The Ranking Model Features
advanced
5m
812
Variational Autoencoders And Latent Sampling
advanced
6m
813
Data leakage: the silent killer
advanced
6m
814
The Bias Variance Decomposition
advanced
6m
815
Monitoring Inference Latency And Cost
advanced
5m
816
Deep Q Networks
advanced
6m
817
Association Rule Mining
advanced
5m
818
Monitoring Data Drift
advanced
6m
819
The LSTM Cell
advanced
6m
820
Paged Attention
advanced
5m
821
The Hard Negative Mining
advanced
5m
822
The Cost versus Accuracy Tradeoff
advanced
6m
823
The T5 Encoder Decoder
advanced
5m
824
The Second Order Methods Newton
advanced
6m
825
The Large Batch Training
advanced
5m
826
The Ensembling Neural Nets
advanced
5m
827
The Feedback Loop Collection
advanced
4m
828
The Matryoshka Embeddings
advanced
6m
829
The Multilingual Embeddings
advanced
6m
830
The RAG Evaluation Metrics Deep
advanced
6m
831
The Instance Segmentation Mask RCNN
advanced
6m
832
Gradient Boosting
advanced
6m
833
Knowledge Distillation
advanced
5m
834
Explainability with SHAP
advanced
5m
835
The Cold Start Problem
advanced
6m
836
Ranking Metrics NDCG And MAP
advanced
6m
837
Gradient Descent Intuition
advanced
5m
838
Train Serve Consistency
advanced
5m
839
Human in the Loop Approval
advanced
5m
840
Gaussian Mixture Models
advanced
5m
841
Change Point Detection
advanced
5m
842
The PageRank Algorithm
advanced
5m
843
The Softmax Temperature In Attention
advanced
5m
844
Privacy Preserving ML
advanced
5m
845
The Reranker Stage
advanced
5m
846
The Temperature Top P Top K
advanced
6m
847
NDCG for Ranking
advanced
6m
848
Stacking Ensembles
advanced
5m
849
The Model Comparison Fairness
advanced
6m
850
Positional Information
advanced
6m
851
The TensorRT Optimization
advanced
5m
852
The Multi Armed Bandit Deployment
advanced
5m
853
The Exploration Strategies Deep Dive
advanced
6m
854
The Rotary Embeddings Deep
advanced
6m
855
The Meta Prompting
advanced
5m
856
The Question Answering Generative
advanced
5m
857
The Diversity And Serendipity
advanced
4m
858
The Eval During Fine Tuning
advanced
6m
859
Model Quantization
advanced
5m
860
The KV Cache
advanced
5m
861
Self Supervised Learning
advanced
5m
862
Variational Autoencoders
advanced
6m
863
Contrastive Language Image Pretraining
advanced
6m
864
Neural Architecture Search
advanced
6m
865
XGBoost Mechanics
advanced
6m
866
Matrix Factorization For Recommendations
advanced
6m
867
BLEU And ROUGE For Text
advanced
6m
868
Canary Deploys For Models
advanced
5m
869
Semantic Search Basics
advanced
5m
870
Feature Scaling at Serving
advanced
5m
871
Multi Agent Collaboration
advanced
5m
872
The Expectation Maximization Algorithm
advanced
5m
873
Semantic Segmentation
advanced
5m
874
The Apriori Algorithm
advanced
5m
875
Multivariate Time Series
advanced
5m
876
Link Prediction
advanced
5m
877
Monitoring Prediction Drift
advanced
6m
878
Query Expansion
advanced
5m
879
The Hallucination Grounding
advanced
6m
880
The BLEU Score for Text
advanced
6m
881
The Attention Mechanism Intro
advanced
6m
882
Bayesian Optimization For Tuning
advanced
5m
883
The Position Bias Correction
advanced
6m
884
The Bias in Language Models
advanced
6m
885
The Class Weighting
advanced
5m
886
NDCG Explained
advanced
6m
887
The Layer and Batch Norm
advanced
5m
888
The Ring All Reduce
advanced
5m
889
The Retrieval Augmented Eval
advanced
7m
890
The Agent Observability Tracing
advanced
6m
891
The Inference Batching Dynamic
advanced
5m
892
The XGBoost Specifics
advanced
5m
893
The Test Time Augmentation
advanced
4m
894
The PPO Clipping Objective Deep Dive
advanced
6m
895
The Retrieval Recall Tuning
advanced
6m
896
The Tensor Parallelism Deep
advanced
6m
897
The Machine Translation Deep
advanced
5m
898
The Recsys Evaluation Offline
advanced
5m
899
Tree of Thoughts Deep Dive
advanced
6m
900
The Prompt Versioning And Testing
advanced
6m
901
Backpropagation
advanced
6m
902
LoRA Adapters
advanced
5m
903
Learning To Rank
advanced
6m
904
Perplexity For Language Models
advanced
5m
905
Fallback And Graceful Degradation For Ml
advanced
5m
906
Agent Guardrails and Sandboxing
advanced
5m
907
Policy Gradient Methods
advanced
6m
908
The Retraining Trigger
advanced
6m
909
The Attention Head Specialization
advanced
5m
910
Federated Learning Basics
advanced
5m
911
Model Parallelism Tensor and Pipeline
advanced
6m
912
The Maximum Likelihood Estimation
advanced
5m
913
The Contextual Bandit
advanced
6m
914
Scaling Inference
advanced
6m
915
The Conjugate Gradient
advanced
6m
916
The Production Readiness Checklist
advanced
6m
917
The Eval Data Contamination
advanced
6m
918
Byte Level Fallback
advanced
5m
919
The SVM Kernels Deep
advanced
5m
920
The Multimodal Embeddings
advanced
6m
921
The Embedding Drift Monitoring
advanced
6m
922
The Flash Attention Deep
advanced
6m
923
The Guardrails In Prompts
advanced
6m
924
The Vision Transformer Deep
advanced
6m
925
The Pipeline Parallelism Deep
advanced
6m
926
The Position Bias Correction Deep
advanced
5m
927
Agent Observability Deep Dive
advanced
6m
928
Quantization Aware Training
advanced
5m
929
The Retrieval Evaluation Metrics
advanced
5m
930
The Graph Of Thoughts
advanced
5m
931
The Merging Models
advanced
6m
932
Mixture of Experts
advanced
5m
933
Generative Adversarial Networks
advanced
6m
934
The Reward Model in RLHF
advanced
6m
935
Statistical Significance In A B Tests
advanced
6m
936
The Data Flywheel
advanced
5m
937
Second Order Methods Overview
advanced
5m
938
The Viterbi Algorithm
advanced
5m
939
The Actor Critic Architecture
advanced
5m
940
The Vision Transformer Patches
advanced
5m
941
Market Basket Analysis
advanced
4m
942
The Message Passing in GNNs
advanced
6m
943
The Structured JSON Output
advanced
6m
944
Handling Imbalanced Data
advanced
6m
945
The Wasserstein GAN
advanced
5m
946
The Prefill and Decode Phases
advanced
5m
947
The A B Testing Statistics
advanced
6m
948
The Probability Calibration
advanced
6m
949
The Offline Online Metric Gap
advanced
6m
950
The Watermarking of Generated Text
advanced
6m
951
The Data Pipeline Monitoring
advanced
5m
952
MAP for Retrieval
advanced
5m
953
The Softmax and Cross Entropy
advanced
5m
954
The Postmortem and Learning
advanced
6m
955
The Zero Redundancy Optimizer
advanced
5m
956
The Agent Trajectory Eval
advanced
7m
957
The Multi GPU Inference
advanced
6m
958
The LightGBM Specifics
advanced
5m
959
The Transfer Learning Fine Tuning
advanced
5m
960
The Agentic RAG
advanced
6m
961
The Prompt Optimization Automated
advanced
6m
962
The CLIP Contrastive Vision
advanced
6m
963
The Flash Attention Memory
advanced
6m
964
Multi Agent Coordination Deep Dive
advanced
6m
965
The Multi Objective Ranking
advanced
6m
966
Detokenization Issues
advanced
5m
967
The Soft Actor Critic Algorithm
advanced
7m
968
The Speculative Decoding Deep
advanced
6m
969
Diffusion Models
advanced
6m
970
GPU Memory and the Roofline Model
advanced
6m
971
The ML Platform Architecture
advanced
7m
972
The Scaling Laws For Transformers
advanced
6m
973
Differential Privacy In Training
advanced
6m
974
The RAG Pipeline End to End
advanced
6m
975
Train Test Leakage Avoidance
advanced
6m
976
The Score Based Models
advanced
5m
977
The Model Selection Criteria
advanced
6m
978
Case Study Recommendation System
advanced
7m
979
The Dual Problem
advanced
6m
980
The KKT Conditions
advanced
6m
981
The CatBoost Specifics
advanced
5m
982
The TRPO Trust Region Method
advanced
7m
983
The Diffusion For Images Deep
advanced
6m
984
Agent Evaluation Harness Deep Dive
advanced
6m
985
Speculative Decoding
advanced
5m
986
Direct Preference Optimization
advanced
6m
987
Retrieval Augmented Generation Pipeline
advanced
6m
988
The Eval Harness for Safety
advanced
6m
989
Metric Gaming and Goodhart Law
advanced
5m
990
Knowledge Graph Embeddings
advanced
6m
991
RLHF Basics
advanced
6m
992
Agentic LLM Workflows
advanced
6m
993
Privacy and Differential Privacy Basics
advanced
6m
994
Proximal Policy Optimization
advanced
6m
995
Classifier Free Guidance
advanced
5m
996
The Tree Of Thoughts
advanced
5m
997
The Graph RAG
advanced
6m