CS601 Machine Learning • Unit 3

Convolutional Neural Network Complete Notes

Complete RGPV exam-oriented Unit 3 notes covering Convolutional Neural Network, flattening, subsampling, padding, stride, convolution layer, pooling layer, loss layer, dense layer, 1x1 convolution, inception network, input channels, transfer learning, one-shot learning, dimension reduction and CNN implementation using TensorFlow and Keras.

Advertisement
Advertisement

Download Unit 3 PDF Notes

Download the complete handwritten-style PDF notes for CS601 Machine Learning Unit 3. These notes are prepared for RGPV students for fast revision, PYQ-based preparation and 7-mark/14-mark answer writing.

Read Document Notes Important Questions PYQ Analysis

Unit 3 Official Syllabus

Convolutional Neural Network, flattening, subsampling, padding, stride, convolution layer, pooling layer, loss layer, dense layer, 1x1 convolution, inception network, input channels, transfer learning, one-shot learning, dimension reduction, implementation of CNN like TensorFlow and Keras.

Why Unit 3 is Important?

Unit 3 is one of the most scoring units of CS601 Machine Learning because it focuses on Convolutional Neural Networks, also known as CNNs. CNNs are widely used in image recognition, face detection, object detection, medical image analysis, self-driving cars and computer vision.

In RGPV exams, CNN architecture, convolution layer, pooling layer, padding, stride, transfer learning and TensorFlow/Keras implementation are frequently asked topics. If students prepare CNN architecture with diagrams, they can easily write strong 7-mark and 14-mark answers.

1. Convolutional Neural Network

Convolutional Neural Network is a deep learning neural network mainly designed for processing image data. It automatically extracts important features from images using convolution and pooling operations.

Exam Definition

A Convolutional Neural Network is a deep neural network that uses convolution layers, pooling layers and dense layers to extract spatial features from images and perform classification or recognition tasks.

Input Image
↓
Convolution Layer
↓
Activation Function
↓
Pooling Layer
↓
Flattening
↓
Dense Layer
↓
Output

Why CNN is Needed?

Memory Trick: CNN = Computer Vision Neural Network.

2. Convolution Layer

The convolution layer is the core layer of CNN. It applies filters on the input image to extract useful features such as edges, corners, shapes and textures.

Input Image
↓
Filter / Kernel
↓
Feature Map

Important Terms

Example

In an image of a face, convolution layer can detect eyes, nose, edges and facial boundaries.

3. Pooling Layer and Subsampling

Pooling layer reduces the size of feature maps while preserving important information. It helps reduce computation and controls overfitting.

Types of Pooling

Pooling Type Meaning
Max Pooling Selects maximum value from selected region.
Average Pooling Takes average value from selected region.
Feature Map
↓
Pooling
↓
Reduced Feature Map
PYQ Tip: Pooling reduces spatial dimensions and computational cost.

4. Padding

Padding means adding extra pixels around the border of an image before applying convolution. It helps preserve image size and prevents loss of border information.

Original Image
↓
Add Zero Border
↓
Padded Image
↓
Convolution

Types of Padding

Importance

5. Stride

Stride defines how many pixels the filter moves at each step during convolution. Larger stride reduces output size, while smaller stride gives more detailed feature maps.

Stride = 1 → Filter moves 1 pixel
Stride = 2 → Filter moves 2 pixels

Effect of Stride

Stride Effect
Small Stride More detailed output
Large Stride Smaller output size

6. Flattening

Flattening converts a multidimensional feature map into a one-dimensional vector. This vector is passed to dense layers for classification.

2D Feature Maps
↓
Flattening
↓
1D Vector
↓
Dense Layer

Why Flattening is Needed?

7. Dense Layer and Loss Layer

Dense layer is a fully connected layer where each neuron is connected to every neuron of the previous layer. It performs final classification based on extracted features.

Loss Layer

Loss layer calculates the difference between predicted output and actual output. The model uses this error to improve training.

Flattened Features
↓
Dense Layer
↓
Prediction
↓
Loss Layer
↓
Error Calculation

8. Input Channels

Input channels represent the number of color channels in an image. A grayscale image has one channel, while a colored RGB image has three channels: Red, Green and Blue.

Image Type Channels
Grayscale Image 1 Channel
RGB Image 3 Channels
RGB Image
↓
Red Channel
Green Channel
Blue Channel

9. 1x1 Convolution

1x1 convolution uses a filter of size 1 by 1. It is mainly used to reduce or increase the number of channels without changing the spatial size of feature maps.

Uses of 1x1 Convolution

Exam Keyword: 1x1 convolution is also called pointwise convolution.

10. Inception Network

Inception Network is a CNN architecture that applies multiple filter sizes in parallel, such as 1x1, 3x3 and 5x5 filters. It allows the network to learn features at different scales.

Input
↓
1x1 Convolution
3x3 Convolution
5x5 Convolution
Pooling
↓
Concatenate
↓
Output

Advantages

11. Transfer Learning

Transfer Learning is a technique where a pre-trained model is reused for a new but related task. Instead of training a model from scratch, we use knowledge learned from a large dataset.

Pre-trained Model
↓
Reuse Learned Features
↓
Fine-Tune on New Dataset
↓
New Prediction Task

Example

A CNN trained on ImageNet can be reused for classifying medical images, animals or handwritten digits with small modifications.

Advantages

12. One-Shot Learning

One-Shot Learning is a machine learning technique where a model learns from only one or very few examples. It is useful when large datasets are not available.

Example

Face recognition systems can identify a person after seeing only one image of that person.

One Example
↓
Feature Comparison
↓
Similarity Matching
↓
Prediction

Applications

13. Dimension Reduction

Dimension reduction is the process of reducing the number of input features while keeping important information. It helps reduce computation and improves model performance.

Need of Dimension Reduction

High-Dimensional Data
↓
Dimension Reduction
↓
Important Features
↓
Efficient Model

Common Method

PCA, or Principal Component Analysis, is one of the most common dimension reduction techniques.

14. CNN Implementation using TensorFlow and Keras

TensorFlow and Keras are popular deep learning libraries used to build and train CNN models. Keras provides a simple high-level interface, while TensorFlow handles numerical computation.

Basic CNN Implementation Flow

  1. Import TensorFlow and Keras libraries.
  2. Load dataset.
  3. Preprocess images.
  4. Create CNN model.
  5. Add convolution and pooling layers.
  6. Add flatten and dense layers.
  7. Compile model.
  8. Train model.
  9. Evaluate accuracy.
model = Sequential()
model.add(Conv2D(32, (3,3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(10, activation='softmax'))
Exam Tip: For theory answer, write steps and architecture instead of writing only code.

Unit 3 PYQ Trend Analysis

Topic PYQ Frequency Importance
CNN Architecture Repeated ★★★★★
Convolution and Pooling Layers Repeated ★★★★★
Padding and Stride Frequently Asked ★★★★
Transfer Learning Often Asked ★★★★
Inception Network Moderate ★★★
TensorFlow and Keras Recently Asked ★★★★
Dimension Reduction Repeated in ML papers ★★★★★
Most expected Unit 3 question: Explain CNN architecture with convolution layer, pooling layer, flattening and dense layer. Unit 3: CNN Most asked topics: CNN architecture Convolution layer Pooling layer Padding Subsampling Transfer learning Inception network TensorFlow implementation Overfitting / underfitting in CNN Expected questions: Explain CNN architecture with diagram. Explain convolution, pooling, padding and stride. Explain implementation of CNN in TensorFlow/Keras. Explain transfer learning and Inception network. Explain overfitting and underfitting in CNN. Importance: Very High

Top 20 Important Questions for Unit 3

  1. Explain Convolutional Neural Network with neat diagram.
  2. Explain CNN architecture in detail.
  3. Explain convolution layer and feature map.
  4. Explain pooling layer and its types.
  5. Explain padding and stride in CNN.
  6. Explain flattening in CNN.
  7. Explain dense layer and loss layer.
  8. Explain input channels in image data.
  9. Explain 1x1 convolution and its uses.
  10. Explain Inception Network.
  11. Explain transfer learning with example.
  12. Explain one-shot learning.
  13. Explain dimension reduction in Machine Learning.
  14. Explain CNN implementation using TensorFlow and Keras.
  15. Differentiate convolution layer and pooling layer.
  16. Differentiate padding and stride.
  17. Explain how CNN extracts hierarchical features.
  18. Explain why pooling reduces spatial dimensions.
  19. Explain role of CNN in computer vision.
  20. Write applications of CNN.

Most Expected Questions 2026

24-Hour Revision Box

CNN
↓
Image Learning Network

Convolution Layer
↓
Feature Extraction

Filter / Kernel
↓
Detects Edges and Patterns

Pooling Layer
↓
Reduces Size

Padding
↓
Protects Border Information

Stride
↓
Filter Movement

Flattening
↓
2D to 1D Vector

Dense Layer
↓
Final Classification

1x1 Convolution
↓
Channel Reduction

Inception Network
↓
Multiple Filters in Parallel

Transfer Learning
↓
Reuse Pre-trained Model

One-Shot Learning
↓
Learn from Few Examples

Dimension Reduction
↓
Reduce Features

TensorFlow / Keras
↓
CNN Implementation

How to Write 7-Mark Answer?

For a 7-mark Unit 3 answer, write definition, diagram, working, advantages and applications. Keep answer around 2 to 3 pages in exam copy. Diagrams are very important for CNN answers.

How to Write 14-Mark Answer?

For a 14-mark answer, write introduction, definition, full architecture diagram, detailed working, layers explanation, advantages, disadvantages, applications and conclusion. CNN architecture and auto feature extraction should be clearly explained.

Related Machine Learning Units

FAQs

What is CNN in Machine Learning?

CNN is a deep learning model used mainly for image processing and computer vision tasks.

Which is the most important topic in Unit 3?

CNN architecture with convolution layer, pooling layer, flattening and dense layer is the most important topic.

Why is pooling used in CNN?

Pooling reduces the size of feature maps and decreases computational cost while preserving important features.

What is transfer learning?

Transfer learning reuses a pre-trained model for a new related task, reducing training time and data requirement.

Is TensorFlow and Keras important for RGPV exams?

Yes, implementation steps of CNN using TensorFlow and Keras can be asked as a 7-mark question.