ERA probably the most exhaustive and updated Deep Vision & NLP Fusion Program in the world!
- A freshly rewritten course accommodating recent breakthroughs in AI research.
- A balanced curriculum that sails through vision and NLP topics, as well as machine learning operations.
- A practical approach where students develop applications and deploy them on the cloud in nearly every session.
- A systematic learning process where every session begins with solving the previous week's assignment and quiz.
- Takes you from basics to SOTA in 9 months
- And much more!
| Session No. | Session Name | Description | Tags |
|---|---|---|---|
| 1 | Fundamentals of Artificial Intelligence | Introduction to neural network concepts, data representation for images, text, and audio, and forward propagation mathematics. | Neural Networks, AI Basics |
| 2 | Exploring Neural Network Architectures | Delve into multi-channel convolutions, max pooling, layer structures, and more. | Convolutions, Architectures |
| 3 | Git and Python Essentials | A primer on Git, GitHub, and Python for effective collaboration and programming in AI projects. | Git, Python |
| 4 | Building the First Neural Networks | Exploring kernels, channels, word embeddings, and GPU processing. | Kernels, Embeddings |
| 5 | Introduction to PyTorch | Grasping PyTorch basics, tensors, AutoGrad, and building a neural network from scratch. | PyTorch, Neural Networks |
| 6 | Backpropagation and Advanced Architectures | Grasping backpropagation mathematics, spatial data loss and recovery, modern AI architectures, and more. | Backpropagation, Advanced Architectures |
| 7 | In-Depth Coding Practice | Hands-on coding exercises and optimization of code performance. | Coding, Performance Optimization |
| 8 | Advanced Techniques and Optimizations | Exploring batch normalization, dropout, word-level masking, regularization, convolution types, and more. | Batch Norm, Dropout |
| 9 | Data Augmentation and Visualization | Understanding data augmentation, preprocessing, tokenization, class activation maps, and visualization techniques. | Data Augmentation, Visualization |
| 10 | PyTorch Lightning and AI Application Development | Learning PyTorch Lightning, Fabric, and creating Lightning-based AI applications. | PyTorch Lightning, AI Development |
| 11 | Residual Connections in CNNs and FC Layers | Examining ResNet and the concept of residual connections in neural networks. | ResNet, Residual Connections |
| 12 | Building and Deploying AI Applications | Creating machine learning pipelines for training and deployment of AI models. | AI Deployment, ML Pipelines |
| 13 | YOLO and Object Detection Techniques | Understanding anchor boxes and the YOLO object detection algorithm. | YOLO, Object Detection |
| 14 | Multi-GPU Training and Scalable Model Serving | Implementing multi-GPU training, dynamic batching, and autoscaling for model serving. | Multi-GPU, Dynamic Batching |
| 15 | UNETs, Variational AutoEncoders, and Applications | Exploring UNETs, variational autoencoders, and their practical applications. | UNETs, AutoEncoders |
| 16 | Transformers and Advanced Embedding Techniques | Studying transformers, self-attention, cross-attention, multi-head attention, and advanced tokenization and embeddings. | Transformers, Embeddings |
| 17 | Encoder Architectures and BERT | Investigating encoder architectures and training BERT models. | BERT, Encoder Architectures |
| 18 | Masked AutoEncoders and Vision Transformers | Learning about masked autoencoders, vision transformers, their architectures, and training techniques. | Vision Transformers, AutoEncoders |
| 19 | Decoders and Generative Pre-trained Transformers | Understanding decoder-only architectures, training GPT/GPT-2 models, and exploring sparse attention. | GPT, Decoders |
| 21 | Training and Fine-tuning Large Language Models | Techniques for training large language models and fine-tuning them on a single GPU. | Large Models, Fine-tuning |
| 22 | CLIP Models and Training | Studying contrastive language-image pre-training, understanding CLIP models, and training them from scratch. | CLIP, Language-Image Pre-training |
| 23 | Generative Art and Stable Diffusion | Exploring the world of generative art and the concept of stable diffusion in AI. | Generative Art, Stable Diffusion |
| 24 | Automatic Speech Recognition Fundamentals | Introduction to Whisper and automatic speech recognition (ASR) technologies. | ASR, Whisper |
| 25 | Reinforcement Learning Part I | Understanding deep Q learning, A3C, and DDPG in reinforcement learning. | Deep Q Learning, Reinforcement Learning |
| 26 | Reinforcement Learning Part II | Exploring advanced reinforcement learning algorithms like T3D and Agent57. | T3D, Agent57 |
| 27 | Reinforcement Learning from Human Feedback | Investigating reinforcement learning from human feedback (RLHF) and language-human alignment in models like ChatGPT. | RLHF, ChatGPT |
| 28 | Training ChatGPT from Scratch | Step-by-step guide to training a ChatGPT model from scratch. | ChatGPT, Training |
| 29 | Training Multimodal GPTs | Techniques and best practices for training multimodal generative pre-trained transformers. | Multimodal, GPTs |
| 30 | Capstone Project | A comprehensive project that amalgamates and applies the knowledge acquired throughout the course. | Project, Application |
- Basic understanding of Python and machine learning concepts
- Familiarity with Git and GitHub