Scribd Logo
Upload

Welcome to Scribd!

  • 18 views

    Advanced Topics in Machine Learning

    Uploaded by

    xx69dd69xx
    This document outlines a course on advanced topics in machine learning. The course focuses on recent advances like generative adversarial networks and variational autoencoders. It covers topics like outlier detection, dimensionality reduction, deep generative models, and attention models. The course aims to help students apply machine learning models to real-world applications and understand recent trends in the field.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Advanced Topics in Machine Learning

    Uploaded by

    xx69dd69xx
    18 views2 pages
    This document outlines a course on advanced topics in machine learning. The course focuses on recent advances like generative adversarial networks and variational autoencoders. It covers topics like outlier detection, dimensionality reduction, deep generative models, and attention models. The course aims to help students apply machine learning models to real-world applications and understand recent trends in the field.

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document outlines a course on advanced topics in machine learning. The course focuses on recent advances like generative adversarial networks and variational autoencoders. It covers topics like outlier detection, dimensionality reduction, deep generative models, and attention models. The course aims to help students apply machine learning models to real-world applications and understand recent trends in the field.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    18 views2 pages

    Advanced Topics in Machine Learning

    Uploaded by

    xx69dd69xx
    This document outlines a course on advanced topics in machine learning. The course focuses on recent advances like generative adversarial networks and variational autoencoders. It covers topics like outlier detection, dimensionality reduction, deep generative models, and attention models. The course aims to help students apply machine learning models to real-world applications and understand recent trends in the field.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 2

    SVKM’s NMIMS

    Mukesh Patel School of Technology Management & Engineering

    Program: B Tech Artificial Intelligence Semester : VII


    Course: Advanced Topics in Machine Learning Code: 702AI0C018
    Teaching Scheme Evaluation Scheme
    Lecture Internal
    Practical Tutorial Term End
    (Hours Credit Continuous
    (Hours (Hours Examinations
    per Assessment (ICA)
    per per (TEE) (Marks-
    week) (Marks - 50)
    week) week) 100)
    2 2 0 3 Scaled to 50 marks Scaled to 50 Marks
    Prerequisite: Basic calculus, Machine Learning, Python Programming
    Course Objective
    Machine Learning and Deep Learning has revolutionized the progress in the field where applications
    are found in NLP, Vision and Speech to name a few domains. This course focuses on the recent advances
    in machine learning, including Generative Adversarial Networks (GAN), Variational Autoencoders, etc.
    Course Outcomes
    After completion of the course, student will be able to -
    1. Explain the mathematical formulation of different learning models
    2. Apply outlier detection and implement dimension reduction methods
    3. Apply generative learning models to real-world applications
    4. Describe attention architecture and recent trends in machine learning
    Detailed Syllabus
    Unit Description Duration
    1. Review of machine learning and deep learning concepts 03
    Parametric vs non-parametric models, Feedforward neural networks,
    Gradient-based Optimization, Regularization, Challenges in Neural Network
    Optimization
    Outlier Detection and Dimensionality Reduction 08
    2 One class SVM, Proximity based Outlier detection: distance and density based
    outlier detection, Applications of Outlier detection, Principal Component
    Analysis (PCA), Applications of PCA, Autoencoders, Denoising
    Autoencoders, Variational Autoencoders, Applications of Autoencoders
    3. Deep Generative Models 07
    Generative vs Discriminative Models, Generative Adversarial Networks
    (GAN), Wasserstein Generative Adversarial Networks, Applications of GAN
    4. Attention Models 07
    Encoder decoder Architecture, Attention Cues, Attention Pooling, Attention
    Scoring Functions, Bahdanau Attention, Self-Attention and Positional
    Encoding Transformer Architecture

    Signature
    (Prepared by Concerned Faculty/HOD)
    B Tech AI / Semester-V / AY 2023-24 / Page
    SVKM’s NMIMS
    Mukesh Patel School of Technology Management & Engineering

    5 Recent Trends in Machine Learning 05


    Zero-shot, One-shot, Few-shot learning, Self-supervised learning,
    Reinforcement learning
    Total 30
    Text Books
    1. Ian Goodfellow, Yoshua Bengio and Aaron Courville, Deep Learning, The MIT Press, 2016.
    2. Kevin Murphy, Machine Learning: A Probabilistic Perspective, Illustrated edition, MIT Press, 2012.
    3. Dive into Deep Learning, d2l.ai
    4. Langr, J., & Bok, V., GANs in action: deep learning with generative adversarial networks, 1st edition,
    Shelter Island, 2019
    5. Charu C. Aggarwal, Outlier Analysis, 2nd edition, Springer, 2017
    Reference Books
    1. Christopher Bishop, Pattern Recognition and Machine Learning, 1st Edition, Springer, 2006.
    Laboratory Work
    8 to 10 programming exercises (and a practicum) based on the syllabus

    Signature
    (Prepared by Concerned Faculty/HOD)
    B Tech AI / Semester-V / AY 2023-24 / Page

    You might also like