Deep Learning and Neural Networks

GMUSD61

Credits: 2.00

Prerequisites : Basic understanding of machine learning concepts and proficiency in Python programming

Course Duration : 30 Hours / 12 Weeks

Start Date : 2024-03-13

End Date : 2024-03-14

Seats Remaining : 60

BACK

Aim & Summary

The course covers fundamental concepts such as perceptrons, activation functions, and backpropagation, as well as advanced topics including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs). Participants will also learn about popular DL frameworks like TensorFlow and PyTorch and gain hands-on experience in implementing neural network models. Through hands-on projects and practical exercises, participants will develop the skills to tackle real-world problems using DL and NN techniques. By the end of the course, participants will be equipped with the knowledge and tools to apply deep learning to a wide range of applications, from computer vision and natural language processing to reinforcement learning and generative modeling.

Course Content
Week 1	Introduction to Deep Learning and Neural Networks
Week 2	Perceptrons and Multilayer Perceptrons (MLPs)
Week 3	Activation Functions and Loss Functions
Week 4	Training Neural Networks: Backpropagation and Gradient Descent
QUIZ 1
Week 5	Convolutional Neural Networks (CNNs) for Image Recognition
Week 6	Recurrent Neural Networks (RNNs) for Sequence Modeling
Week 7	Introduction to TensorFlow and Keras
Week 8	Introduction to PyTorch
QUIZ 2
Week 9	Advanced Topics in Deep Learning: Generative Adversarial Networks (GANs), Reinforcement Learning
Week 10	Transfer Learning and Fine-Tuning Pretrained Models
Week 11	Deploying Deep Learning Models: TensorFlow Serving, ONNX
Week 12	Ethical Considerations and Future Directions in Deep Learning
PROJECT REPORT

Deep Learning and Neural Networks

Aim & Summary

Course Certification