Course Outcomes (COs):
| Course Outcomes | |
| CO1 | To implement modern deep learning architectures including CNNs, RNNs, Transformers, and Generative Models. |
| CO2 | To explore and implement the sequence modlling algorithms are BPTT, LSTM, GRU and application in NLP. |
- Multilayer Perceptron, Gradient Descent, Backpropagation,
- Neural Networks.
- Convolutional Neural Networks: LeNet, AlexNet.
- Recurrent Neural Networks: Back propagation through time, Long Short Term Memory, Gated Recurrent Units
- Generative models: Restrictive Boltzmann Machines (RBMs), Introduction to MCMC and Gibbs Sampling, gradient computations in RBMs, Deep Boltzmann Machines.
- Variational Auto encoders, Generative Adversarial Networks, Multi-task Deep Learning, Multi-view Deep Learning.
- Transformers: Transfer learning, data augmentation and hyper parameter search.
CO–PO Mapping:
| PO1 | PO2 | PO3 | PO4 | PO5 | PO6 | PO7 | PO8 | PO9 | PO10 | PO11 | PO12 | |
| CO1 | 3 | 3 | 3 | 3 | 3 | |||||||
| CO2 | 2 | 2 | 2 | 3 | 3 |
H