Course Title: Deep Learning and Artificial Intelligence Credit Units: 4 Course Code

You might also like

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 4

Annexure ‘CD – 01’

L T P/S SW OL/FW No. of TOTAL


Course Title: Deep Learning and Artificial Credit Units: 4 PSDA CREDIT
Intelligence UNITS
- - - - 8 - 4
Course Level: UG Course Code:

Course Objectives:
The main objective of this course is to make students comfortable with proper methods to collect the data, employ the correct analysis,
and effectively present the results using Statistics. They will be introduced to Python programming along with various libraries used in it.
The students will also get familiar with the various concepts of Deep Learning and Computer vision. They will be able to develop neural
networks and different models successfully in python.

Pre-requisites: Basic knowledge of programming, Statistics and advanced mathematics, Problem-solving Techniques

Course Contents/Syllabus:
Weightage (%)
Module 1: Introduction to Machine Learning
History and definition of ML and AI, Installation and setup of Python, Introduction to Pandas, Introduction to Numpy,
Introduction to Matplotlib, Linear Algebra in python, Probability, Descriptive statistics, Data Visualization, Data pre-
processing, Data transformation, Data standardization, Feature extraction, Proximity measures, Introduction to various 10
ML algorithms, Types of Machine learning, Applications of ML

Module II: Statistics & Basics of Machine learning


Measures of Central Tendency: Mean, Median, Mode, Measures of Dispersion: Absolute deviation from mean, Standard
Deviation, Variance, Range, Quartiles, Skewness, Random Experiment, Sample space, Random Variables, Probability,
Conditional Probability, Independence, Expectation, Variance, Probability Distribution, Factor, Odds v/s Probability, 10
Hypothesis testing, t-test, ANOVA, Chi-square test, Correlation, Normalization
Module III: Introduction to Neural Networks
Introduction to Neural Networks its types and applications, Introduction to Keras, Introduction to ANN Perceptron and
its uses Multi-Layer Perceptron & Deep Neural Network, Activation Function, TanH function, Sigma, Relu, etc. 20
Understanding activation function and how it works, Feed Forward Network Activation Function & Feed-Forward
Network, Cost function, Backpropagation, Gradient Descent, Regularization & Dropout Technique, Batch
Normalization
Module IV: Types of Neural Networks & NLP
Understanding Convolutional neural network, Introduction to CNN Pooling, Steps in CNN, Pooling, Convolutional
layers, Flattening and Full connection, Preparing a fully connected neural network, Hands-on with CNN and
implementation on Python, Introduction to RNN, Deep RNN, Training of Deep RNNs, Long Short Term Memory, 30
GRU, Transfer Learning, Hands-on with RNN, Introduction to NLP, Applications of NLP, Stages of NLP, Syntactic
Learning, Semantic Analysis, Bag of Words, Word Embeddings, Word2Vec, Hands-on with
NLP (Text classification)

Module V: Introduction to Computer Vision


What is Image?, Introduction to OpenCV Basics, Opening Image files in a notebook and with OpenCV,
Drawing on Images (Basic Shapes, Text, and Polygons), Direct Drawing on Images with a mouse, Image 30
Basics Assessment and Solutions, Color Mappings, Blending and Pasting Images, Image Thresholding,
Blurring, and Smoothing, Morphological Operators, Gradients, Histograms, Histogram Equalization, Image
Processing Assessment, and Solutions, Connecting to Camera, Using Video Files, Drawing on Live Camera,
Video Basics Assessment and Solutions, Optical Flow and it's Coding with OpenCV, MeanShift and
CamShift Tracking Theory and Implementation with OpenCV, Overview of various Tracking API Methods
and Implementation with OpenCV

Course Learning Outcomes:

On the successful completion of the course, the student will be able to


1. Identify the relevant ML algorithm based on the problemset
2. Apply statistical techniques to analyse data
3. Apply neural networks for problem solving
4. Use relevant type of neural network to solve problems
5. Use OpenCV to analyse images

Pedagogy for Course Delivery:

The class will be taught using remote teaching methodology. The class will be taught using theory, practical and case study method.
FieldWork / Online(OL) Assessment

S.No. Type Component Name Marks


1 External END TERM EXAMINATION 100.00

Text Reading & References:

1 Hands-On Unsupervised Learning with Python by Giuseppe Bonaccorso – Packt publication


2 Python Deep Learning by Daniel Slater, Gianmario Spacagna and Peter Roelants – Packt Publication
3 Machine Learning with Tensorflow by Nishant Shukla
4 Deep Learning with Keras by Antonio Gulli and Sujit Pal
5 Machine Learning for OpenCV by Micheal Beyeler
Mapping Continuous Evaluation Components/PSDA with CLOs

Understanding
Remembering

Evaluating

Creating
Analyzing
Applying
Bloom’s Level →

Course Learning Outcomes


Assessment CLO1 CLO2 CLO3 CLO4 CLO5 CLO 6
type/ PSDA
Mid Term Exam √ √ √ √ √ √

Home Assignment √ √ √ √

Q Quiz √ √ √ √ √

V Viva-Voce √ √ √ √ √

You might also like