This document provides information about a Machine Learning course offered at National University of Sciences & Technology. The 3 credit hour course is offered in the 2nd semester to MSEE-AI & Autonomous Systems students. The course aims to introduce deep neural networks and train students on tools like PyTorch, Keras and TensorFlow. It will cover architectures like AlexNet, ResNet and GANs. The course also focuses on limitations and vulnerabilities of deep learning models. Students will learn to design, implement and analyze deep learning algorithms through assignments, a semester project and exams.
This document provides information about a Machine Learning course offered at National University of Sciences & Technology. The 3 credit hour course is offered in the 2nd semester to MSEE-AI & Autonomous Systems students. The course aims to introduce deep neural networks and train students on tools like PyTorch, Keras and TensorFlow. It will cover architectures like AlexNet, ResNet and GANs. The course also focuses on limitations and vulnerabilities of deep learning models. Students will learn to design, implement and analyze deep learning algorithms through assignments, a semester project and exams.
This document provides information about a Machine Learning course offered at National University of Sciences & Technology. The 3 credit hour course is offered in the 2nd semester to MSEE-AI & Autonomous Systems students. The course aims to introduce deep neural networks and train students on tools like PyTorch, Keras and TensorFlow. It will cover architectures like AlexNet, ResNet and GANs. The course also focuses on limitations and vulnerabilities of deep learning models. Students will learn to design, implement and analyze deep learning algorithms through assignments, a semester project and exams.
This document provides information about a Machine Learning course offered at National University of Sciences & Technology. The 3 credit hour course is offered in the 2nd semester to MSEE-AI & Autonomous Systems students. The course aims to introduce deep neural networks and train students on tools like PyTorch, Keras and TensorFlow. It will cover architectures like AlexNet, ResNet and GANs. The course also focuses on limitations and vulnerabilities of deep learning models. Students will learn to design, implement and analyze deep learning algorithms through assignments, a semester project and exams.
Download as DOCX, PDF, TXT or read online from Scribd
Download as docx, pdf, or txt
You are on page 1/ 3
National University of Sciences & Technology (NUST)
School of Electrical Engineering and Computer Science (SEECS)
Department of Electrical Engineering
Machine Learning Course Code: SE-801 Semester: 2nd Credit Hours: 3+0 Prerequisite Codes: Fundamentals of machine learning Instructor: Wajahat Hussain Class: MSEE-AI & Autonomous Systems Office: SEECS 218 Telephone: Lecture Days: Tuesday and Wednesday E-mail: [email protected] Class Room: Consulting Hours: Lab Engineer: N/A Lab Engineer Email: N/A Knowledge Group: CS Core Updates on LMS: After every lecture
Course Description: Deep learning has revolutionized multiple disciplines. Multiple well established hand crafted systems are being replaced with data driven pipelines. The excitement generated by deep learning needs caution. Deep systems are vulnerable to adversarial attacks. This course is about introduction of deep neural networks, how to train these networks and understand their vulnerabilities.
Course Objectives: The aim of this course is to understand the basics of deep neural networks including multiple well known architectures (Alexnet, Resnet, Inception, and GAN). Special emphasis on gaining hands-on capability on latest deep learning tools (Pytorch, Keras, Tensorflow, Colab). Vulnerabilities and limitations of deep networks will be discussed.
Course Learning Outcomes (CLOs):
At the end of the course the students will be able to: PLO BT Level* 1. Describe and design deep learning algorithms 2 C-3 2. Understand limitations of deep learning algorithms 4 C-3 3. Implement deep learning algorithms 5 C-3 * BT= Bloom’s Taxonomy, C=Cognitive domain, P=Psychomotor domain, A= Affective domain
Page 1 of 3 National University of Sciences & Technology (NUST) School of Electrical Engineering and Computer Science (SEECS) Department of Electrical Engineering
Mapping of CLOs to Program Learning Outcomes
CLO1 CLO2 CLO3 CLO4
PLOs/CLOs PLO 1 (Engineering Knowledge) PLO 2 (Problem Analysis) √ PLO 3 (Design/Developments of Solutions) PLO 4 (Investigation) √ PLO 5 (Modern Tool Usage) √ PLO 6(The Engineer and Society) PLO 7 (The Environment and Sustainability) PLO 8 (Ethics) PLO 9 (Individual and Team Work) PLO 10 (Communication) PLO 11 (Project Management) PLO 12 (Life Long Learning)
Mapping of CLOs to Assessment Modules and Weightages (In accordance with NUST statutes) To be filled in at the end of the course. CLO1 CLO2 CLO3 Assessments/CLOs Theory: 100%
Assignments: 10% √ √ √ Mid Term: 30% √
Semester Project: 10% √
End Semester Exam: 50% √ √ √ Total : 100 %
Books: Text Book: 1. Lecture Notes. 2. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow by Aurelien Geron Reference 1. Coursera ML course by Andrew Ng. Material:
3 Introduction to Tensorflow I CLO 3 4 Introduction to Tensorflow II CLO 3 5 Introduction to CNN (AlexNet, Resnet) CLO 1
Page 2 of 3 National University of Sciences & Technology (NUST) School of Electrical Engineering and Computer Science (SEECS) Department of Electrical Engineering
6 OHT-1 7 Introduction to Pytorch I CLO 3 8 Introduction to Pytorch II CLO 3 9 Processing sequences using RNNs CLO 1 10 Autoencoders & GANs CLO 1 11 Adversarial attacks on Deep Networks CLO 2 12 OHT-2 13 Adversarial attacks on Deep Networks II CLO 2 14 Reinforment learning CLO 1 15 Federated Learning CLO 1 16 Discussion on semester project/ research papers CLO 3 17 Discussion on semester project/ research papers CLO 3 18 Week 18: ESE
Grading Policy: Quiz Policy: The quizzes will be unannounced and normally last for ten minutes. The question framed is to test the concepts involved in last few lectures. Number of quizzes (around 6) that will be used for evaluation is at the instructor’s discretion. All assignments will count towards the total. No ‘best-of’ policy. Assignment Policy: In order to develop comprehensive understanding of the subject, assignments will be given. Late assignments will not be accepted / graded. All assignments will count towards the total (No ‘best-of’ policy). The students are advised to do the assignment themselves. Copying of assignments is highly discouraged and violations will be dealt with severely by referring any occurrences to the disciplinary committee. The questions in the assignment are meant to be challenging to give students confidence and extensive knowledge about the subject matter and enable them to prepare for the exams. The assignments will be programming based. Evaluation will be viva based. Plagiarism: NUST maintains a zero tolerance policy towards plagiarism. While collaboration in this course is highly encouraged, you must ensure that you do not claim other people’s work/ ideas as your own. Plagiarism occurs when the words, ideas, assertions, theories, figures, images, programming codes of others are presented as your own work. You must cite and acknowledge all sources of information in your assignments. Failing to comply with the NUST plagiarism policy will lead to strict penalties including zero marks in assignments and referral to the academic coordination office for disciplinary action.
Full Download (Ebook) Learn TensorFlow 2.0: Implement Machine Learning and Deep Learning Models with Python by Pramod Singh , Avinash Manure ISBN 9781484255582, 1484255585 PDF DOCX
Code, Et Tu - LLM, Transformer, RAG AI - Mastering Large Language Models, Transformer Models, and Retrieval-Augmented Generation (RAG) Technology (2024)
