Scribd
Upload
16 views2 pages

Arificial Neural Networks Deep Learning Lab CSF

The document outlines a lab course on Artificial Neural Networks and Deep Learning at the University of Engineering & Applied Science, aimed at BSc students in Artificial Intelligence. It details the course objectives, learning outcomes, required textbooks, and a weekly schedule of topics to be covered, including various neural network architectures and deep learning techniques. The course emphasizes practical skills in algorithm analysis, design, and application of deep learning methods.

Uploaded by

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

Arificial Neural Networks Deep Learning Lab CSF

The document outlines a lab course on Artificial Neural Networks and Deep Learning at the University of Engineering & Applied Science, aimed at BSc students in Artificial Intelligence. It details the course objectives, learning outcomes, required textbooks, and a weekly schedule of topics to be covered, including various neural network architectures and deep learning techniques. The course emphasizes practical skills in algorithm analysis, design, and application of deep learning methods.

Uploaded by

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

UNIVERSITY OF ENGINEERING & APPLIED SCIENCE

(U-EAS), SWAT
Department of Computer Systems Engineering

Artificial Neural Networks and Deep Learning (lab)


Course Code: Semester:
Credit Hours: 1 Class:
Instructor: Email:
Office: Program: BS Artificial Intelligence

Course Description
This lab provides BSc students with a comprehensive understanding and practical implementation of
algorithm analysis techniques, equipping them with the skills necessary to analyze and evaluate the
efficiency and performance of algorithms.

Course Objectives
The objectives of this lab are:
● Provide a comprehensive understanding of ANNs in AI, including architecture, mathematical
models, and major types, to lay a strong foundation.
● Enable students to design and apply ANNs for classification problems, emphasizing practical
skills in training, optimization, and effective problem-solving techniques.
● Enable students to design and apply deep learning, such as convolutional and recurrent
networks, unsupervised learning, and reinforcement learning, to expand students' knowledge
and application capabilities.

Course Learning Outcomes (CLOs) for BS Artificial Intelligence


At the end of the course the students will be able to: PLO Domain Taxonomy

Practice deep learning algorithms to real-world


CLO-1 5 Psychomotor P3
problems by using tools..
Observe results from deep learning to select
CLO-2 2 Affective A2
appropriate solutions.
Develop the novel neural network
architectures from scratch and evaluating the
CLO-3 3 Psychomotor P6
performance on application specific standard
benchmarks

Books
Text Book:
● Artificial Neural Networks and Deep Learning Lab manual

Reference Book:
● An Introduction to Neural Networks, James A Anderson, Publisher: A Bradford Book (March
16, 1995), ISBN-10: 0262011441

Topic to be covered
Week
#
UNIVERSITY OF ENGINEERING & APPLIED SCIENCE
(U-EAS), SWAT
Department of Computer Systems Engineering
1 Scientific Python (A)
2 Scientific Python (B)
3 Neural Networks
4 Perceptron, Multi-Layer Perceptron, Adaline
5 Shallow vs. Deep Learning
6 Reinforcement Learning, Hebbian Learning, Kohonen Self Organizing Maps
7 Hopfield & Bi-Directional Network and Associative Memory
8 Boltzmann machines, Restricted Boltzmann Machines
Mid Term Exam
9 Unsupervised deep learning including auto-encoders

10 Deep convolutional neural networks

11 Hyperparameter selection, Gradient descent rule

12 Training Deep CNN for Object Classification

13 Training Deep CNN for Object Detection


14 Training Deep CNN for Segmentation

15 Deep Recurrent Neural Networks


16 Deep Sequential Neural Networks
Final Term Exam

You might also like