Data Science: Transformers for Natural Language Processing

  • Welcome
  • Introduction
Introduction
04:02
Outline
09:16
Where to get the code
02:06
Are You Beginner, Intermediate, or Advanced? All are OK!
05:01
Temporary 403 Errors
02:58
Beginner's Corner Section Introduction
10:14
From RNNs to Attention and Transformers - Intuition
17:01
Sentiment Analysis
10:32
Sentiment Analysis in Python
17:00
Embeddings and Semantic Search
08:24
Embeddings and Semantic Search in Python
34:50
Text Generation
10:47
Text Generation in Python
11:47
Masked Language Modeling (Article Spinner)
11:37
Masked Language Modeling (Article Spinner) in Python
08:26
Named Entity Recognition (NER)
04:53
Named Entity Recognition (NER) in Python
09:49
Text Summarization
05:15
Text Summarization in Python
07:00
Neural Machine Translation
06:18
Neural Machine Translation in Python
09:50
Question Answering
07:20
Question Answering in Python
06:14
Zero-Shot Classification
05:30
Zero-Shot Classification in Python
13:47
Beginner's Corner Section Summary
04:53
Suggestion Box
03:10
Fine-Tuning Section Introduction
04:30
Text Preprocessing and Tokenization Review
13:35
Models and Tokenizers
15:22
Models and Tokenizers in Python
13:16
Transfer Learning & Fine-Tuning (pt 1)
09:29
Transfer Learning & Fine-Tuning (pt 2)
10:37
Transfer Learning & Fine-Tuning (pt 3)
10:08
Fine-Tuning Sentiment Analysis and the GLUE Benchmark
12:22
Fine-Tuning Sentiment Analysis in Python
19:36
Fine-Tuning Transformers with Custom Dataset
15:04
Hugging Face AutoConfig
05:45
Fine-Tuning with Multiple Inputs (Textual Entailment)
07:16
Fine-Tuning Transformers with Multiple Inputs in Python
07:36
Fine-Tuning Section Summary
03:13
Token Classification Section Introduction
06:58
Data & Tokenizer (Code Preparation)
05:04
Data & Tokenizer (Code)
07:45
Target Alignment (Code Preparation)
09:57
Create Tokenized Dataset (Code Preparation)
03:46
Target Alignment (Code)
10:09
Data Collator (Code Preparation)
03:42
Data Collator (Code)
03:15
Metrics (Code Preparation)
06:47
Metrics (Code)
05:40
Model and Trainer (Code Preparation)
02:26
Model and Trainer (Code)
03:27
POS Tagging & Custom Datasets (Exercise Prompt)
05:18
POS Tagging & Custom Datasets (Solution)
18:16
Token Classification Section Summary
02:02
Translation Section Introduction
04:34
Data & Tokenizer (Code Preparation)
05:35
Things Move Fast
01:48
Data & Tokenizer (Code)
06:16
Aside: Seq2Seq Basics (Optional)
10:39
Model Inputs (Code Preparation)
08:15
Model Inputs (Code)
08:05
Translation Metrics (BLEU Score & BERT Score) (Code Preparation)
03:52
Translation Metrics (BLEU Score & BERT Score) (Code)
05:43
Train & Evaluate (Code Preparation)
04:34
Train & Evaluate (Code)
05:00
Translation Section Summary
02:39
Question-Answering Section Introduction
04:50
Exploring the Dataset (SQuAD)
04:20
Exploring the Dataset (SQuAD) in Python
05:05
Using the Tokenizer
08:30
Using the Tokenizer in Python
11:55
Aligning the Targets
14:53
Aligning the Targets in Python
16:15
Applying the Tokenizer
09:56
Applying the Tokenizer in Python
10:39
Question-Answering Metrics
03:46
Question-Answering Metrics in Python
02:41
From Logits to Answers
21:23
From Logits to Answers in Python
16:14
Computing Metrics
05:30
Computing Metrics in Python
05:49
Train and Evaluate
02:53
Train and Evaluate in Python
05:45
Question-Answering Section Summary
04:00
Theory Section Introduction
05:06
Basic Self-Attention
09:35
Self-Attention & Scaled Dot-Product Attention
18:02
Attention Efficiency
04:36
Attention Mask
03:56
Language Model Training Efficiency
15:30
Multi-Head Attention
07:13
Transformer Block
06:45
Positional Encodings
07:16
Encoder Architecture
06:23
Decoder Architecture
10:58
Encoder-Decoder Architecture
08:31
BERT
04:52
GPT
06:45
GPT-2
06:30
GPT-3
05:14
ChatGPT
06:33
GPT-4
03:00
Theory Section Summary
04:50
Implementation Section Introduction
05:57
Encoder Implementation Plan & Outline
06:11
How to Implement Multihead Attention From Scratch
12:33
How to Implement the Transformer Block From Scratch
02:15
How to Implement Positional Encoding From Scratch
05:14
How to Implement Transformer Encoder From Scratch
04:38
Train and Evaluate Encoder From Scratch
13:32
How to Implement Causal Self-Attention From Scratch
05:08
How to Implement a Transformer Decoder (GPT) From Scratch
04:40
How to Train a Causal Language Model From Scratch
18:55
Implement a Seq2Seq Transformer From Scratch for Language Translation (pt 1)
12:30
Implement a Seq2Seq Transformer From Scratch for Language Translation (pt 2)
16:15
Implement a Seq2Seq Transformer From Scratch for Language Translation (pt 3)
16:45
Implementation Section Summary
01:40
Beginner Q&A: Can We Use GPT-4 For Everything?
27:13
Do People Still Use BERT?
02:28
Pre-Installation Check
04:13
Anaconda Environment Setup
20:21
How to install Numpy, Scipy, Matplotlib, Pandas, PyTorch, and TensorFlow
17:33
How to Code Yourself (part 1)
15:55
How to Code Yourself (part 2)
09:24
Proof that using Jupyter Notebook is the same as not using it
12:29
How to use Github & Extra Coding Tips (Optional)
11:12
How to Succeed in this Course (Long Version)
10:25
Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?
22:05
What order should I take your courses in? (part 1)
11:19
What order should I take your courses in? (part 2)
16:07
What is the Appendix?
02:48
Where to get discount coupons and FREE deep learning material
05:49
Introduction
04:02
Outline
09:16
Where to get the code
02:06
Are You Beginner, Intermediate, or Advanced? All are OK!
05:01
Temporary 403 Errors
02:58
Beginner's Corner Section Introduction
10:14
From RNNs to Attention and Transformers - Intuition
17:01
Sentiment Analysis
10:32
Sentiment Analysis in Python
17:00
Embeddings and Semantic Search
08:24
Embeddings and Semantic Search in Python
34:50
Text Generation
10:47
Text Generation in Python
11:47
Masked Language Modeling (Article Spinner)
11:37
Masked Language Modeling (Article Spinner) in Python
08:26
Named Entity Recognition (NER)
04:53
Named Entity Recognition (NER) in Python
09:49
Text Summarization
05:15
Text Summarization in Python
07:00
Neural Machine Translation
06:18
Neural Machine Translation in Python
09:50
Question Answering
07:20
Question Answering in Python
06:14
Zero-Shot Classification
05:30
Zero-Shot Classification in Python
13:47
Beginner's Corner Section Summary
04:53
Suggestion Box
03:10
Fine-Tuning Section Introduction
04:30
Text Preprocessing and Tokenization Review
13:35
Models and Tokenizers
15:22
Models and Tokenizers in Python
13:16
Transfer Learning & Fine-Tuning (pt 1)
09:29
Transfer Learning & Fine-Tuning (pt 2)
10:37
Transfer Learning & Fine-Tuning (pt 3)
10:08
Fine-Tuning Sentiment Analysis and the GLUE Benchmark
12:22
Fine-Tuning Sentiment Analysis in Python
19:36
Fine-Tuning Transformers with Custom Dataset
15:04
Hugging Face AutoConfig
05:45
Fine-Tuning with Multiple Inputs (Textual Entailment)
07:16
Fine-Tuning Transformers with Multiple Inputs in Python
07:36
Fine-Tuning Section Summary
03:13
Token Classification Section Introduction
06:58
Data & Tokenizer (Code Preparation)
05:04
Data & Tokenizer (Code)
07:45
Target Alignment (Code Preparation)
09:57
Create Tokenized Dataset (Code Preparation)
03:46
Target Alignment (Code)
10:09
Data Collator (Code Preparation)
03:42
Data Collator (Code)
03:15
Metrics (Code Preparation)
06:47
Metrics (Code)
05:40
Model and Trainer (Code Preparation)
02:26
Model and Trainer (Code)
03:27
POS Tagging & Custom Datasets (Exercise Prompt)
05:18
POS Tagging & Custom Datasets (Solution)
18:16
Token Classification Section Summary
02:02
Translation Section Introduction
04:34
Data & Tokenizer (Code Preparation)
05:35
Things Move Fast
01:48
Data & Tokenizer (Code)
06:16
Aside: Seq2Seq Basics (Optional)
10:39
Model Inputs (Code Preparation)
08:15
Model Inputs (Code)
08:05
Translation Metrics (BLEU Score & BERT Score) (Code Preparation)
03:52
Translation Metrics (BLEU Score & BERT Score) (Code)
05:43
Train & Evaluate (Code Preparation)
04:34
Train & Evaluate (Code)
05:00
Translation Section Summary
02:39
Question-Answering Section Introduction
04:50
Exploring the Dataset (SQuAD)
04:20
Exploring the Dataset (SQuAD) in Python
05:05
Using the Tokenizer
08:30
Using the Tokenizer in Python
11:55
Aligning the Targets
14:53
Aligning the Targets in Python
16:15
Applying the Tokenizer
09:56
Applying the Tokenizer in Python
10:39
Question-Answering Metrics
03:46
Question-Answering Metrics in Python
02:41
From Logits to Answers
21:23
From Logits to Answers in Python
16:14
Computing Metrics
05:30
Computing Metrics in Python
05:49
Train and Evaluate
02:53
Train and Evaluate in Python
05:45
Question-Answering Section Summary
04:00
Theory Section Introduction
05:06
Basic Self-Attention
09:35
Self-Attention & Scaled Dot-Product Attention
18:02
Attention Efficiency
04:36
Attention Mask
03:56
Language Model Training Efficiency
15:30
Multi-Head Attention
07:13
Transformer Block
06:45
Positional Encodings
07:16
Encoder Architecture
06:23
Decoder Architecture
10:58
Encoder-Decoder Architecture
08:31
BERT
04:52
GPT
06:45
GPT-2
06:30
GPT-3
05:14
ChatGPT
06:33
GPT-4
03:00
Theory Section Summary
04:50
Implementation Section Introduction
05:57
Encoder Implementation Plan & Outline
06:11
How to Implement Multihead Attention From Scratch
12:33
How to Implement the Transformer Block From Scratch
02:15
How to Implement Positional Encoding From Scratch
05:14
How to Implement Transformer Encoder From Scratch
04:38
Train and Evaluate Encoder From Scratch
13:32
How to Implement Causal Self-Attention From Scratch
05:08
How to Implement a Transformer Decoder (GPT) From Scratch
04:40
How to Train a Causal Language Model From Scratch
18:55
Implement a Seq2Seq Transformer From Scratch for Language Translation (pt 1)
12:30
Implement a Seq2Seq Transformer From Scratch for Language Translation (pt 2)
16:15
Implement a Seq2Seq Transformer From Scratch for Language Translation (pt 3)
16:45
Implementation Section Summary
01:40
Beginner Q&A: Can We Use GPT-4 For Everything?
27:13
Do People Still Use BERT?
02:28
Pre-Installation Check
04:13
Anaconda Environment Setup
20:21
How to install Numpy, Scipy, Matplotlib, Pandas, PyTorch, and TensorFlow
17:33
How to Code Yourself (part 1)
15:55
How to Code Yourself (part 2)
09:24
Proof that using Jupyter Notebook is the same as not using it
12:29
How to use Github & Extra Coding Tips (Optional)
11:12
How to Succeed in this Course (Long Version)
10:25
Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?
22:05
What order should I take your courses in? (part 1)
11:19
What order should I take your courses in? (part 2)
16:07
What is the Appendix?
02:48
Where to get discount coupons and FREE deep learning material
05:49

Not getting something? Want to ask a question? Visit the course Q&A

Github link Back to main course page and lecture list
Start learning today

Join 30 day bootcamp for free

4.7/5 from — 600k+ learners