NLP-CV.AJ1
Transformers for Natural Language Processing and Computer Vision
Master Transformers for NLP and CV, from architecture to Generative AI with GPTs, ViT, and Stable Diffusion. Build, fine-tune, and deploy.
- Practice in 27 Laboratorios prácticos — nothing to install
- 21 Lecciones interactivas y 135 topics mapped to the official exam objectives
Intermediate A tu propio ritmo · 1 año de acceso
27 LiveLabs prácticos
Practice real IT tasks in guided environments.
- Entornos reales
- Calificación automática
- Sin instalación
01 / Habilidades que obtendrás
What you will be able to do
Transformer Architecture Mastery: Deeply understand the 'Attention Is All You Need' paradigm, encoder-decoder structures, and how to implement foundational Transformer Models like BERT and RoBERTa from scratch, including their pretraining and fine-tuning nuances.
Generative AI Development: Gain practical expertise in leveraging and fine-tuning cutting-edge Generative AI models such as OpenAI GPTs (GPT-4, RAG), T5 for summarization, and exploring advanced LLMs like PaLM 2, understanding their capabilities and inherent limitations.
Computer Vision with Transformers: Develop proficiency in applying Vision Transformer (ViT) models, CLIP, and DALL-E for multimodal tasks, and master text-to-image generation with Stable Diffusion, including automated prompt design and training vision models without coding via Hugging Face AutoTrain.
Advanced Deployment & Risk Mitigation: Learn to interpret transformer behavior using tools like BertViz and SHAP, implement LLM embeddings as an alternative to fine-tuning, and critically assess and mitigate risks associated with large language models, paving the way for functional AGI.
Course Highlights
-
21 Lecciones estructuradas Cobertura completa de los objetivos principales del curso
-
27 LiveLabs prácticos Escenarios interactivos guiados con evaluación instantánea
-
1 año de acceso completo Aprendizaje a tu propio ritmo, accesible en cualquier momento y en todos los dispositivos
02 / Lecciones y laboratorios
See exactly what you will learn and practice
Plan de estudios
21 Lecciones interactivas · 135 topics01 Preface 2 topics +
- Who this course is for
- What this course covers
02 What are Transformers? 6 topics · 1 Laboratorio en vivo +
- Foundation Models
- A brief history of how transformers were born
- The new role of AI professionals
- The rise of seamless transformer APIs
- Summary
- References
1 Laboratorio en vivo in this lesson — see the labs panel →
03 Getting Started with the Architecture of the Transformer Model 5 topics · 2 Laboratorio en vivo +
- The rise of the Transformer: Attention Is All You Need
- Training and performance
- Hugging Face transformer models
- Summary
- References
2 Laboratorio en vivo in this lesson — see the labs panel →
04 Emergent vs Downstream Tasks: The Unseen Depths of Transformers 5 topics · 2 Laboratorio en vivo +
- The paradigm shift: What is an NLP task?
- Investigating the potential of downstream tasks
- Running downstream tasks
- Summary
- References
2 Laboratorio en vivo in this lesson — see the labs panel →
05 Advancements in Translations with Google Trax, Google Translate, and Gemini 7 topics · 1 Laboratorio en vivo +
- Defining machine translation
- Evaluating machine translations
- Translations with Google Trax
- Translation with Google Translate
- Translation with Gemini
- Summary
- References
1 Laboratorio en vivo in this lesson — see the labs panel →
06 Diving into Fine-Tuning through BERT 5 topics · 1 Laboratorio en vivo +
- The architecture of BERT
- Fine-tuning BERT
- Building a Python interface to interact with the model
- Summary
- References
1 Laboratorio en vivo in this lesson — see the labs panel →
07 Pretraining a Transformer from Scratch through RoBERTa 6 topics · 2 Laboratorio en vivo +
- Training a tokenizer and pretraining a transformer
- Building KantaiBERT from scratch
- Pretraining a Generative AI customer support model on X data
- Next steps
- Summary
- References
2 Laboratorio en vivo in this lesson — see the labs panel →
08 The Generative AI Revolution with ChatGPT 7 topics · 3 Laboratorio en vivo +
- GPTs as GPTs
- The architecture of OpenAI GPT transformer models
- OpenAI models as assistants
- Getting started with the GPT-4 API
- Retrieval Augmented Generation (RAG) with GPT-4
- Summary
- References
3 Laboratorio en vivo in this lesson — see the labs panel →
09 Fine-Tuning OpenAI GPT Models 9 topics +
- Risk management
- Fine-tuning a GPT model for completion (generative)
- Preparing the dataset
- Fine-tuning an original model
- Running the fine-tuned GPT model
- Managing fine-tuned jobs and models
- Before leaving
- Summary
- References
10 Shattering the Black Box with Interpretable Tools 6 topics · 2 Laboratorio en vivo +
- Transformer visualization with BertViz
- Interpreting Hugging Face transformers with SHAP
- Transformer visualization via dictionary learning
- Other interpretable AI tools
- Summary
- References
2 Laboratorio en vivo in this lesson — see the labs panel →
11 Investigating the Role of Tokenizers in Shaping Transformer Models 4 topics · 1 Laboratorio en vivo +
- Matching datasets and tokenizers
- Exploring sentence and WordPiece tokenizers to u...fficiency of subword tokenizers for transformers
- Summary
- References
1 Laboratorio en vivo in this lesson — see the labs panel →
12 Leveraging LLM Embeddings as an Alternative to Fine-Tuning 6 topics · 2 Laboratorio en vivo +
- LLM embeddings as an alternative to fine-tuning
- Fundamentals of text embedding with NLTK and Gensim
- Implementing question-answering systems with embedding-based search techniques
- Transfer learning with Ada embeddings
- Summary
- References
2 Laboratorio en vivo in this lesson — see the labs panel →
13 Toward Syntax-Free Semantic Role Labeling with ChatGPT and GPT-4 9 topics · 1 Laboratorio en vivo +
- Getting started with cutting-edge SRL
- Entering the syntax-free world of AI
- Defining SRL
- SRL experiments with ChatGPT with GPT-4
- Questioning the scope of SRL
- Redefining SRL
- From task-specific SRL to emergence with ChatGPT
- Summary
- References
1 Laboratorio en vivo in this lesson — see the labs panel →
14 Summarization with T5 and ChatGPT 8 topics · 1 Laboratorio en vivo +
- Designing a universal text-to-text model
- The rise of text-to-text transformer models
- A prefix instead of task-specific formats
- The T5 model
- Text summarization with T5
- From text-to-text to new word predictions with OpenAI ChatGPT
- Summary
- References
1 Laboratorio en vivo in this lesson — see the labs panel →
15 Exploring Cutting-Edge LLMs with Vertex AI and PaLM 2 6 topics +
- Architecture
- Assistants
- Vertex AI PaLM 2 API
- Fine-tuning
- Summary
- References
16 Guarding the Giants: Mitigating Risks in Large Language Models 9 topics · 3 Laboratorio en vivo +
- The emergence of functional AGI
- Cutting-edge platform installation limitations
- Auto-BIG-bench
- WandB
- When will AI agents replicate?
- Risk management
- Risk mitigation tools with RLHF and RAG
- Summary
- References
3 Laboratorio en vivo in this lesson — see the labs panel →
17 Beyond Text: Vision Transformers in the Dawn of Revolutionary AI 7 topics · 2 Laboratorio en vivo +
- From task-agnostic models to multimodal vision transformers
- ViT – Vision Transformer
- CLIP
- DALL-E 2 and DALL-E 3
- GPT-4V, DALL-E 3, and divergent semantic association
- Summary
- References
2 Laboratorio en vivo in this lesson — see the labs panel →
18 Transcending the Image-Text Boundary with Stable Diffusion 6 topics · 1 Laboratorio en vivo +
- Transcending image generation boundaries
- Part I: Defining text-to-image with Stable Diffusion
- Part II: Running text-to-image with Stable Diffusion
- Part III: Video
- Summary
- References
1 Laboratorio en vivo in this lesson — see the labs panel →
19 Hugging Face AutoTrain: Training Vision Models without Coding 8 topics · 1 Laboratorio en vivo +
- Goal and scope of this lesson
- Getting started
- Uploading the dataset
- Training models with AutoTrain
- Deploying a model
- Running our models for inference
- Summary
- References
1 Laboratorio en vivo in this lesson — see the labs panel →
20 On the Road to Functional AGI with HuggingGPT and its Peers 8 topics · 1 Laboratorio en vivo +
- Defining F-AGI
- Installing and importing
- Validation set
- HuggingGPT
- CustomGPT
- Model Chaining with Runway Gen-2
- Summary
- References
1 Laboratorio en vivo in this lesson — see the labs panel →
21 Beyond Human-Designed Prompts with Generative Ideation 6 topics +
- Part I: Defining generative ideation
- Part II: Automating prompt design for generative image design
- Part III: Automated generative ideation with Stable Diffusion
- The future is yours!
- Summary
- References
Laboratorios prácticos Our edge
27 Laboratorio en vivos- Training, Evaluating, and Visualizing a Machine Learning Classifier
- Implementing Multi-Head Attention and Post-Layer Normalization
- Exploring Positional Encoding in Transformer Models
- Visualizing Decision Boundaries with k-NN Using 1000 Random Samples
- Running Downstream Transformer Tasks
- Preprocessing the WMT14 French-English Dataset and Evaluating with BLEU
- Fine-Tuning BERT for Sentence Classification Using the CoLA Dataset
- Building and Training KantaiBERT for Token Classification
- Building a Customer-Support Assistant Using a Transformer Model
- Analyzing GPT Transformer Architecture and OpenAI Model APIs
- Getting Started with OpenAI GPT-4 for NLP Tasks
- Implementing RAG Using GPT-4
- Visualizing Transformer Attention with BertViz
- Interpreting Transformer Predictions Using SHAP
- Exploring Tokenizers in Modern NLP Using HuggingFace
- Building Word Embeddings Using NLTK and Gensim
- Building an Embedding-Based Question-Answering and Transfer-Learning Pipeline
- Performing Zero-Shot SRL Using GPT-4 Via Prompting
- Building and Evaluating Text Summarization Systems
- Evaluating Auto-BIG-bench Tasks
- Evaluating and Mitigating Hallucination in RAG Systems
- Mitigating Risks in Generative AI Systems
- Exploring Vision-Language Models with CLIP and ViT
- Generating and Interpreting AI-Driven Visual Content Using GPT-4V and DALL·E
- Generating Images with Stable Diffusion Using Keras
- Training NLP Models Automatically with Hugging Face AutoTrain
- Analyzing Images Using ViT Models
03 / Preguntas frecuentes
Preguntas antes de empezar
Who is this course designed for? +
What are the practical applications covered? +
<
p dir="ltr">You'll build and fine-tune models for machine translation, text summarization, question-answering systems, semantic role labeling, and cutting-edge text-to-image generation. We also cover integrating with APIs like GPT-4 and Vertex AI PaLM 2 for real-world Generative AI solutions.
Does this course cover the latest Transformer models? +
Absolutely. We dive into the architecture and application of current models like BERT, RoBERTa, T5, OpenAI GPTs (including GPT-4 and RAG), Vision Transformer (ViT), CLIP, DALL-E 3, Stable Diffusion, and PaLM 2, ensuring you're up-to-date with the Generative AI landscape.
What are the limitations or challenges addressed in the course? +
We explicitly address critical aspects like the trade-offs in fine-tuning vs. embeddings, the role of tokenizers in model performance, interpreting black-box models, and significant risks associated with large language models, including ethical considerations and platform limitations. Expect to learn how to debug and mitigate common failure points.
Keep going
You might also like
Ready to Build the Future of Multimodal AI?
The line between text and vision is disappearing. Start your journey to becoming a lead AI architect and master Transformers for NLP and CV to stay ahead in the rapidly evolving Generative AI landscape.
- 1 año de acceso completo
- 27 LiveLab incluido
- Certificado de finalización
No se requiere tarjeta de crédito