Deep & Reinforcement Learning Unit 3

CS702(B) Unit 3 CNN Architectures and Deep Learning Trends study material for RGPV CSE 7th Semester. Learn Greedy Layerwise Pre-training, activation functions, weight initialization, word representations, CNN, LeNet, AlexNet, ZF-Net, VGGNet, GoogLeNet, ResNet, Guided Backpropagation, Deep Dream and Deep Art.

View Topics Resources Questions

Unit 3 Overview

Unit 3 focuses on modern deep learning architectures, especially Convolutional Neural Networks. It explains CNN evolution from LeNet to ResNet, better activation functions, better weight initialization, word representations and visualization techniques like Guided Backpropagation, Deep Dream and Deep Art.

🧠

Deep Learning Improvements

Study pre-training, activation functions, weight initialization and word representations.

🖼️

CNN Architectures

Learn LeNet, AlexNet, ZF-Net, VGGNet, GoogLeNet and ResNet.

🔍

Visualization Techniques

Understand Guided Backpropagation, Deep Dream, Deep Art and recent DL trends.

Unit 3 Topics Covered

Complete syllabus-based topics of Deep & Reinforcement Learning Unit 3.

Greedy Layerwise Pre-training

Greedy layerwise pre-training trains deep networks one layer at a time before fine-tuning the complete model.

Better Activation Functions

Improved activation functions like ReLU, Leaky ReLU and ELU help deep networks learn faster and reduce gradient problems.

Better Weight Initialization

Good weight initialization helps neural networks converge faster and prevents vanishing or exploding gradients.

Vectorial Representations of Words

Word representations convert words into numerical vectors so that neural networks can understand semantic relationships.

Convolutional Neural Networks

CNNs are deep learning models mainly used for image processing, feature extraction and computer vision tasks.

Convolution Layer

The convolution layer applies filters to input images to detect features like edges, corners and patterns.

Pooling Layer

Pooling reduces feature map size and helps make CNNs more efficient and less sensitive to small changes.

LeNet

LeNet is one of the earliest CNN architectures, mainly used for handwritten digit recognition.

AlexNet

AlexNet popularized deep CNNs by achieving major success in image classification using ReLU, dropout and GPUs.

ZF-Net

ZF-Net improved AlexNet by tuning filter sizes and strides for better feature visualization and performance.

VGGNet

VGGNet uses many small 3x3 convolution filters and deep architecture for improved image recognition.

GoogLeNet

GoogLeNet introduced inception modules to improve computational efficiency and multi-scale feature extraction.

ResNet

ResNet uses residual connections to train very deep networks and reduce degradation problems.

Visualizing CNN

CNN visualization helps understand what features are learned by different layers of the network.

Guided Backpropagation

Guided Backpropagation visualizes important input regions that strongly activate neurons in a CNN.

Deep Dream

Deep Dream enhances patterns learned by neural networks to visualize what a model has learned.

Deep Art

Deep Art applies neural style transfer to combine content of one image with style of another image.

Recent Trends in Deep Learning

Recent trends include transformers, attention-based models, self-supervised learning and large-scale pretrained models.

Quick Revision

CNN: Image data ke liye feature extraction based deep learning model.

LeNet: Early CNN for digit recognition.

AlexNet: Deep CNN breakthrough using ReLU, dropout and GPU training.

VGGNet: Deep network with small 3x3 filters.

GoogLeNet: Inception module based CNN.

ResNet: Residual connections se very deep networks train karta hai.

Download Study Resources

📘

Detailed Notes

Download Notes

Important Questions

Download Questions
📄

PYQ Analysis

Download PYQ

Important Questions

  1. Explain Greedy Layerwise Pre-training.
  2. Explain better activation functions used in deep learning.
  3. Explain better weight initialization methods.
  4. Explain vectorial representations of words.
  5. Define CNN and explain its architecture.
  6. Explain convolution layer and pooling layer.
  7. Explain LeNet architecture.
  8. Explain AlexNet architecture.
  9. Explain ZF-Net architecture.
  10. Explain VGGNet architecture.
  11. Explain GoogLeNet and inception module.
  12. Explain ResNet and residual connections.
  13. Differentiate between AlexNet and VGGNet.
  14. Differentiate between VGGNet and ResNet.
  15. Explain CNN visualization techniques.
  16. Explain Guided Backpropagation.
  17. Explain Deep Dream.
  18. Explain Deep Art.
  19. Explain recent trends in Deep Learning architectures.
  20. Write short note on CNN architectures from LeNet to ResNet.

PYQ Analysis Table

Topic Expected Frequency Importance
CNN Architecture Very High ⭐⭐⭐⭐⭐
Convolution & Pooling Layer Very High ⭐⭐⭐⭐⭐
LeNet High ⭐⭐⭐⭐
AlexNet Very High ⭐⭐⭐⭐⭐
VGGNet Very High ⭐⭐⭐⭐⭐
GoogLeNet High ⭐⭐⭐⭐
ResNet Very High ⭐⭐⭐⭐⭐
Guided Backpropagation Medium ⭐⭐⭐
Deep Dream & Deep Art Medium ⭐⭐⭐
Recent Deep Learning Trends High ⭐⭐⭐⭐

FAQs

What is CNN?

CNN is a deep learning model used mainly for image recognition, feature extraction and computer vision tasks.

What is LeNet?

LeNet is an early CNN architecture used for handwritten digit recognition.

What is AlexNet?

AlexNet is a deep CNN architecture that became popular for image classification using ReLU, dropout and GPU training.

What is ResNet?

ResNet is a CNN architecture that uses residual connections to train very deep networks.

What is Deep Dream?

Deep Dream is a visualization technique that enhances patterns learned by a neural network.