Location

Community Services & Continuing Education - Alexandria

Objectives

• Establish a solid foundation in deep learning concepts, with a focus on practical implementation using PyTorch.Learn to build and train neural networks, exploring essential components such as activation functions, optimizers, and loss functions.Understand and apply specialized neural network architectures like CNNs and RNNs for various data types, including images and sequential data.Gain insights into advanced topics like transfer learning, natural language processing, and generative models, expanding the scope of deep learning applications

Outcomes

Proficiency in Deep Learning with PyTorch: Understand the foundational principles of deep learning and develop practical skills in implementing neural networks using PyTorch.Neural Network Building Skills: Build and train neural networks in PyTorch, handling model architecture, forward and backward passes, and model optimization.Understanding of CNNs and RNNs: Implement and utilize CNNs for image data and RNNs for sequential data analysis.Advanced Deep Learning Applications: Apply advanced techniques such as transfer learning, NLP, and generative models to diverse deep learning tasks.Model Evaluation and Improvement: Assess and improve model performance using appropriate evaluation metrics and tuning techniques in PyTorch.

Course Contents

Introduction to Deep Learning Concepts and PyTorch: Covers the basics of deep learning, including neural network structure and key terminology, and introduces PyTorch as a framework for building and training models. Building Neural Networks with PyTorch: Focuses on constructing neural network layers in PyTorch, covering model initialization, forward and backward passes, and basic training loops. Activation Functions, Optimizers, and Loss Functions in PyTorch: Explores the functions essential for neural network performance, including activation functions (e.g., ReLU, Sigmoid), optimizers (e.g., SGD, Adam), and loss functions.Convolutional Neural Networks (CNNs) with PyTorch: Introduces CNNs for image data, including convolutional layers, pooling, and feature extraction techniques. Advanced CNN Architectures and Transfer Learning in PyTorch: Covers advanced CNN architectures (e.g., ResNet, VGG) and transfer learning techniques for leveraging pre-trained models on new tasks. R