Deep Learning Fundamentals

Home >Courses >Deep Learning Fundamentals

Mentor Based

Program Syllabus

Module 1

About This Course

This program introduces the core concepts of deep learning, focusing on neural network architectures, optimization techniques, and common applications. Participants will gain a strong understanding of how to implement and train deep learning models, including hands-on practice using Python and deep learning frameworks like TensorFlow and PyTorch.

Module 2

Aim

To provide a comprehensive introduction to the foundational concepts of deep learning for PhD scholars, researchers, and data professionals. This course covers key architectures, algorithms, and practical applications of deep learning techniques, enabling participants to build and train neural networks for a variety of complex tasks.

Module 3

Program Objectives

Understand the fundamental concepts of deep learning.
Build and train deep neural networks using popular frameworks.
Learn key architectures like CNNs and RNNs for specific tasks.
Apply optimization techniques for improving deep learning models.
Gain hands-on experience with real-world deep learning projects.

Module 4

Program Structure

Introduction to Deep Learning
- Overview of Deep Learning
- Historical Context and Current Trends
- Applications of Deep Learning (e.g., NLP, CV, Autonomous Systems)
Neural Networks Basics
- Neurons, Activation Functions
- Feedforward Networks
- Backpropagation and Gradient Descent
Training Deep Neural Networks
- Loss Functions
- Optimizers (SGD, Adam, etc.)
- Overfitting and Regularization (Dropout, Batch Normalization)
Convolutional Neural Networks (CNNs)
- Introduction to CNNs
- Convolution, Pooling Layers
- Architectures like AlexNet, VGG, ResNet
Recurrent Neural Networks (RNNs)
- Sequence Modeling
- LSTM, GRU, and Attention Mechanisms
- Applications in NLP and Time Series
Deep Learning Frameworks
- Introduction to TensorFlow and PyTorch
- Building Models in TensorFlow/PyTorch
- Customizing Layers and Loss Functions
Autoencoders and Generative Models
- Introduction to Autoencoders
- Variational Autoencoders (VAE)
- Generative Adversarial Networks (GANs)
Advanced Deep Learning Concepts
- Transfer Learning
- Reinforcement Learning Basics
- Transformers and BERT
Model Deployment and Production
- Model Serving
- Model Optimization (Quantization, Pruning)
- Using Models in Real-World Applications (APIs, Cloud, Edge)
Deep Learning Ethics and Fairness
- Bias in AI Models
- Ethical Considerations in AI
- AI for Social Good

Lead Instructor

Dr. Sarah Chen

PhD in Computational Mechanics from MIT with 15+ years of experience in Industrial AI. Former Lead Data Scientist at Tesla and current advisor to Fortune 500 manufacturing firms.