Deep Learning for Computer Vision
Supervised and Unsupervised Learning
Classification and Regression
Convolutional Neural Networks
What You Will Learn
Core Concepts: Classification, Regression, Gradient Descent, and Backpropagation.
Neural Networks: In-depth study of Convolutional Neural Networks (CNNs), including classic architectures like VGGNet and ResNet.
Object Detection: Techniques and models such as Faster-RCNN, YOLOv2, YOLOv5, and YOLOv7.
Generative Models: Exploration of Variational Autoencoders (VAE) and Generative Adversarial Networks (GANs).
Hands-On, Project-Based Learning, gain experience with essential tools like Python, Pytorch, and Tensorflow.
Coding Intensive: You must be a "coding person." You will be required to read and write code for exercises, exams, and projects.
Deep Learning Architecture and Applications
Generative Adversarial Networks (GANs)
Transformers
The curriculum is designed to give you a robust understanding of state-of-the-art deep learning models. Key topics include:
Generative Models: Explore AutoEncoders, Variational AutoEncoders (VAE) , a variety of GANs (like CycleGAN and StyleGAN2) , and image generation with Stable Diffusion and Prompts.
Transformer Architectures: Start with an introduction to the Transformer and advance to models like the Vision Transformer, BERT, Swin Transformer, and Detection Transformer.
Large-Scale Models: Learn about the models powering modern AI, including CLIP, Large Language Models (LLM), and Vision Language Models (VLM).