Scribd
Upload
4 views2 pages

SYLABUS

Uploaded by

prasanar2021aids
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views2 pages

SYLABUS

Uploaded by

prasanar2021aids
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

DEPARTMENT OF ARTIFICIAL INTELLIGENCE AND DATA SCIENCE

COURSE INFORMATION SHEET


DEEP LEARNING MODELS AND AI ANALYST

Course Objective (s):


The purpose of learning this course is to:
1 Understand the concepts of Advanced Machine Learning and Deep Learning
2 Understand the Artificial Intelligence Components
3 Apply the algorithms to implement Neural Networking models.
4 Understand the techniques of Face recognition, self-driving cars
5 Investigate applications of Multilayer perceptron, CNN and RNN

UNIT I PREFACE TO ML-DL MODELS & IBM CLOUD 9


Machine Learning-Deep Learning-Difference between Machine Learning and Deep Learning--Supervised,
Unsupervised and reinforcement-Over fitting and Regression-Classification-Clustering-Parametric vs non-
Parametric models-Linear model - Introduction to IBM cloud- Resources-IBM Cloud Infrastructure-
Security-IBM Cloud Foundry-Cloud Park for data- IBM cloud vs Amazon cloud - Cloud Native Storage and
Data Service
UNIT II NLP AND WATSON STUDIO 9
Introduction to Watson studio- Project creation- Storage- Access control- Prebuilt Watson application-
Watson Solutions- Catalog and govern data - NLP Overview - NLP Explained - Virtual Agents Overview -
Virtual Agents for the Enterprise - Implementing NLP.
UNIT III COMPUTER VISIONS WITH WATSON STUDIOS 9
Watson knowledge studio and Watson knowledge catalog-Watson Discovery Services-Watson Auto AI-
Watson Open Scale- Visual recognition- Watson API - Computer Vision Overview - AI Vision through
Deep Learning - Computer Vision for the Enterprise - Deep learning ecosystem.
UNIT IV MODEL IMPLEMENTATION USING TENSORFLOW 9
TensorFlow Introduction-Tensor Data Structure -Various Dimensions-Tensor handling and Manipulation-
Tensor flow implementation of CNN and RNN-Tensor flow-Word Embedding- evaluating a machine
learning model
UNIT V IMAGE RECOGNITION AND FUTURE OF AI 9
Image Classification -Tensor flow features- import tensor or other libraries-Pickle-Sklearn-Explore Dataset
-Load data using Keras Utility-Visualize the data - Artificial Intelligence Trends - Limits of machine and
human - AI predictions in the next 5 years -Building a network
LIST OF EXPERIMENTS 15
1. Decision tree Classification using Scikit Learn.
2. Theano for computing a Logistic function.
3. Calculate Data Loss using Tensor.
4. Classify Handwritten digits using MNIST dataset.
5. Image Manipulation using Scipy.
6. Predict the color red or white using Keras.
7. Classify objects using Tensor flow.
8. Speech to Text and Text to Speech using IBM and Google APIs
9. Implementing Linear Regression using Python
10. Evaluating Logistic Regression
11. Performance Evaluation using K-Means Clustering
12. Weather Prediction using Naive Bayes classification
Text Books
1 IBM Course ware
References
Deep Learning From Scratch: Building with Python from First Principles by Seth Weidman published
1
by O'Reilley
2 Deep learning in Python/ Pytorch by Manning Publications
3 Artificial Intelligence: A Modern Approach by Stuart Russell, Peter Norvig

4 Introduction to Artificial Intelligence by Philip C. Jackson Jr.

Web References
1 https://developer.ibm.com/technologies/deep-learning/
Expected Outcome of the Course

Course Outcome (s) (COs):


At the end of this course, learners will be able to:
CO1 Understand collections of Advanced Machine learning algorithms and AI basics
Identify the Deep learning Algorithm which is more appropriate for various types of modern
CO2
datasets
CO3 Understanding Perceptron's and how it is used along Computer Vision

You might also like