Resources!

Hello,

these are the official solutions and problem sets!

• Ass0 | Sols
• Ass1 | Sols
• Ass2 | Sols
• Ass3 | Sols

• An Overview of Gradient Descent Optimisation Algorithms
• Parameter Optimisation in Neural Networks

• Visualising Convolutional Neural Networks - Layer by Layer
• How to Visualise Filters and Feature Maps in Convolutional Neural Networks
• A Beginner's Guide to Understanding Convolutional Neural Networks
• An Intuitive Explanation of Convolutional Neural Networks

• LeNet
• AlexNet
• VGG-Net
• ResNet
• DenseNet
• MobileNet

• Understanding Natural Language Processing
• Understanding Long Short-Term Memory (LSTM)
• Illustrated Guide to LSTM's and GRU's
• Visualising memorisation in RNNs
• exploRNN: teaching RNNs through visual exploration
• Word Vectors
• The Illustrated Word2Vec
• The Unreasonable Effectiveness of Recurrent Neural Networks
• GloVe: Global Vectors for Word Representation
• Relational Recurrent Neural Networks
• Blog - Attention? Attention!
• Blog - The Illustrated Transformer by Jay Alammar
• Blog - Language Models
• Neural Machine Translation by Jointly Learning to Align and Translate
• PyTorch - Text classification with the torch text library
• PyTorch - NLP from scratch: Translation with a Sequence to Sequence Network and Attention

• Transformer Paper - Attention is All You Need
• ELMO
• GPT
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• XLM
• XLNet
• GPT-2
• RoBERTa
• Megatron-LM
• T5
• Turing-NLG
• GPT-3
• Llama 3
• Gemini
• Gemma
• Mistral
• Mixtral
• Ollama
• Tower

• Deep Reinforcement Learning: Pong to Pixels
• CARLA - Open source simulator for autonomous driving research
• Using Deep Q-Learning to learn how to play Flappy Bird
• PyGame - Learning Environment
• The Arcade Learning Environment
• Opensim
• Mario-AI
• Deep reinforcement learning based trading agent
• A (Long) Peek into Reinforcement Learning
• A thorough introduction to reinforcement learning
• Reinforcement Learning from Scratch
• Illustrating Reinforcement Learning from Human Feedback
• Tensorforce: A TensorfFlow library for applied reinforcement learning

• Intro to Autoencoders - TensorFlow Tutorial
• Variational Autoencoders
• Convolutional Variational Autoencoder - TensorFlow Tutorial
• Deep Convolutional Generative Adversarial Network (DCGAN) - TensorFlow Tutorial
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (DCGAN)
• Neural Style Transfer - TensorFlow Tutorial
• HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
• pix2pix: Image-to-image translation with a conditional GAN
• CycleGAN
• StyleGAN

• Frontiers of Multimodal Learning: A Responsible AI Approach
• Multimodal AI - Google
• Demo - Azure AI Image Captioning
• Demo - Generating Image Captions
• TensorFlow Tutorial - Image Captioning with Attention
• HuggingFace Demo - Visual Question Answering
• Demo - Visual Question Answering
• Multimodal Embeddings
• Hybrid Procedural Semantics For Visual Question Answering
• Visual Dialog
• The Dialogue must go on: Improving Visual Dialogue via Generative Pre-Training

• OpenAI GPT-4
• OpenAI DALL-E 3
• OpenAI Sora - Creating Videos from Text
• OpenAI Whisper - Automatic Speech Recognition
• Google PaLM 2
• Google Gemini
• Meta Llama 3
• Midjourney: Text to Image Generator
• Stable Diffusion
• MusicLM: Generating Music from Text
• Alphacode
• Synthesia: Text to Videos
• Adobe Firefly
• Cohere: Build conversational agent with RAG

My own notes on many of these research papers can be found on the research papers page.