Skip to main content
grasp.study
About
Explore
Pricing
Log in
Try it for free
Back to course
👋
Welcome to a Grasp lesson
Create a free account
to keep studying and create your own study path.
Gate Data Science and AI
·
Module 11
Deep Learning with PyTorch
1
Implementing the Full Forward Pass
Implement the full forward pass of a feedforward neural network to compute predictions and loss.
2
Backpropagation: Computing Gradients
Explain the backpropagation algorithm for computing gradients.
3
Optimizing Neural Networks with SGD and Adam
Train a neural network using stochastic gradient descent (SGD) and its variants like Adam.
4
Building a Feedforward Neural Network in PyTorch
Build a feedforward neural network for a classification task using PyTorch.
5
PyTorch Training Loop: From Data to Weights
Implement a complete training loop in PyTorch, including data loading, forward/backward passes, and weight updates.
6
CNN Architecture for Image Data
Describe the architecture of Convolutional Neural Networks (CNNs) for image data.
7
Building and Training a Simple CNN for Image Classification
Build and train a simple CNN for an image classification task (e.g., on MNIST).
8
RNN and LSTM Architectures for Sequence Data
Describe the architecture of Recurrent Neural Networks (RNNs) and LSTMs for sequence data.
Previous module
Advanced Machine Learning Models
Next module
Artificial Intelligence: Search and Reasoning