05:40

Marginal, Joint and Conditional Probabilities Explained

04:49

Least Squares vs Maximum Likelihood

03:50

AI Reading List (by Ilya Sutskever) - Part 5

04:27

AI Reading List (by Ilya Sutskever) - Part 4

04:48

AI Reading List (by Ilya Sutskever) - Part 3

05:02

AI Reading List (by Ilya Sutskever) - Part 2

04:31

AI Reading List (by Ilya Sutskever) - Part 1

08:03

Vector Database Search - Hierarchical Navigable Small Worlds (HNSW) Explained

05:40

Singular Value Decomposition (SVD) Explained

03:27

ROUGE Score Explained

05:48

BLEU Score Explained

03:38

Cross-Validation Explained

03:51

Sliding Window Attention (Longformer) Explained

03:36

BART Explained: Denoising Sequence-to-Sequence Pre-training

20:28

RLHF: Training Language Models to Follow Instructions with Human Feedback - Paper Explained

27:43

Chain-of-Verification (COVE) Reduces Hallucination in Large Language Models - Paper Explained

13:59

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits - Paper Explained

05:14

LLM Tokenizers Explained: BPE Encoding, WordPiece and SentencePiece

03:15

Hyperparameters Tuning: Grid Search vs Random Search

26:16

Jailbroken: How Does LLM Safety Training Fail? - Paper Explained

02:44

Word Error Rate (WER) Explained - Measuring the performance of speech recognition systems

03:15

Spearman Correlation Explained in 3 Minutes

03:40

Two Towers vs Siamese Networks vs Triplet Loss - Compute Comparable Embeddings

08:11

LLM Prompt Engineering with Random Sampling: Temperature, Top-k, Top-p

03:21

Kullback-Leibler (KL) Divergence Mathematics Explained

04:36

Covariance and Correlation Explained

07:35

Eigendecomposition Explained

07:24

Multi-Head Attention (MHA), Multi-Query Attention (MQA), Grouped Query Attention (GQA) Explained

04:32

Kabsch-Umeyama Algorithm - How to Align Point Patterns

04:03

How to Fine-tune Large Language Models Like ChatGPT with Low-Rank Adaptation (LoRA)

04:54

Discrete Fourier Transform (DFT and IDFT) Explained in Python

02:55

XGBoost Explained in Under 3 Minutes

03:56

Why Batch Normalization (batchnorm) Works

04:57

Object Detection Part 8: Grounding DINO, Open-Set Object Detection

04:49

Gaussian Mixture Models (GMM) Explained

10:15

Fourier Transform Formula Explained

04:28

Object Detection Part 7: Detection Transformers (DETR), Object Queries

05:07

Object Detection Part 6: The Hungarian Matching Algorithm, Tracking, Bounding Box Matching

06:06

Capsule Networks Explained | Why Using Pooling is a Bad Idea

04:43

Object Detection Part 5: You Only Look Once (YOLO), YOLOv1 Architecture

08:52

Why We Don't Use the Mean Squared Error (MSE) Loss in Classification

05:45

Object Detection Part 4: Mask RCNN, Mask Prediction Branch and Region of Interest Align (ROIAlign)

05:55

Why Language Models Hallucinate

05:33

Object Detection Part 3: Faster R-CNN, Region Proposal Network and Intersection over Union

03:41

Object Detection Part 2: Fast R-CNN, Region Projection and Region of Interest (RoI) Pooling Layer

05:40

Object Detection Part 1: R-CNN, Sliding Window and Selective Search

07:18

How to Select the BEST Threshold for Your Model Using the ROC Curve

06:21

Why We Divide by N-1 in the Sample Variance (Standard Deviation) Formula | The Bessel's Correction

04:18

The Brier Score Explained | Model Calibration

04:09

Gradient Boosting with Regression Trees Explained

04:02

Measuring Artificial Intelligence (AI) Fairness - Disparate Impact Explained

04:47

Why Models Overfit and Underfit - The Bias Variance Trade-off

02:58

Spectral Features - Deltas and Delta-Deltas Explained

05:37

Why Deep Neural Networks (DNNs) Underperform Tree-Based Models on Tabular Data

04:23

Bagging vs Boosting - Ensemble Learning In Machine Learning Explained

08:19

AMSGrad - Why Adam FAILS to Converge

03:27

AdamW Optimizer Explained | L2 Regularization vs Weight Decay

01:54

Why AI Winters Happen....

14:48

Adversarial Discriminative Domain Adaptation (ADDA) Paper Explained

05:32

Why We Perform Feature Scaling In Machine Learning