User:Pinakinathc

Contents

 * 1) Introduction to Deep Learning
 * 2) * Gradient Backpropagation
 * 3) * Optimisation (e.g., SGD, Adam, AdamW, RMSProp etc.)
 * 4) * Reinforcement Learning
 * 5) Neural Networks Architectures
 * 6) * Convolutional neural networks (CNNs).
 * 7) * Transformers.
 * 8) * Graph neural networks.
 * 9) * Graph convolutional neural networks.
 * 10) Training a neural network (start coding yourself).
 * 11) * A simple image classifier using CNN.
 * 12) * A simple text-based image retrieval using CNN.
 * 13) * Using a deep learning framework like PyTorch.
 * 14) * Large-scale training of Foundation Models.
 * 15) Object Detection
 * 16) * Supervised training methods.
 * 17) * Weakly supervised training methods.
 * 18) * Using large-scale foundation models.
 * 19) Probability and Information Theory in Deep Learning
 * 20) * Variational AutoEncoding (VAEs).
 * 21) * Flow-based Models.
 * 22) * Diffusion Models.
 * 23) * Generative Flow Models.
 * 24) Basic Concepts in 3D Geometry
 * 25) * Camera Parameters (e.g., Intrinsics and Extrinsics)
 * 26) * Polar Coordinates
 * 27) * Generate 3D objects using Signed Distance Fields (SDFs).
 * 28) * Generate 3D objects using Neural Radiance Fields (NeRFs).
 * 29) * Generate 3D objects using Gaussian Splatting.