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.
Feuille de route complète LM
·
Module 12
Introduction to Deep Learning Architectures
1
Understanding 2D Convolution and Kernels
Explain the 2D convolution operation and the purpose of kernels/filters.
2
CNN Architecture and Pooling Layers
Describe the architecture of a Convolutional Neural Network (CNN), including pooling layers.
3
Image Classification with CNNs: A MNIST Example
Build and train a basic CNN for image classification on a simple dataset (e.g., MNIST).
4
Transfer Learning with Pretrained Models
Explain the concept of transfer learning with pretrained models.
5
Transfer Learning with ResNet
Adapt a pretrained CNN (e.g., ResNet) for a new image classification task.
6
RNN Architecture and Sequence Applications
Describe the architecture of a simple Recurrent Neural Network (RNN) and its application to sequences.
7
Understanding Vanishing Gradients in RNNs
Explain the vanishing gradient problem in RNNs.
8
Gated Recurrent Units: Tackling Vanishing Gradients
Describe how LSTMs and GRUs address the vanishing gradient problem through gating mechanisms.
End of course,
Back to course
Previous module
Training Neural Networks with PyTorch
Next module