Scribd Logo
Upload

Welcome to Scribd!

  • 72 views

    ML and Deep Learning Syllabus

    Uploaded by

    Padmini Palli
    This 40-50 hour machine learning and deep learning course costs 25,000 rupees. The course provides an introduction to fundamental machine learning and deep learning concepts, algorithms, and hands-on practice in Python. Key topics include supervised and unsupervised learning, neural networks, convolutional neural networks, and applications in image processing, natural language processing and more. Regular attendance and participation are required along with practice on a laptop or desktop. Upon completing the course, students should understand a variety of algorithms and be able to apply machine learning to real-world problems.

    Copyright:

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

    ML and Deep Learning Syllabus

    Uploaded by

    Padmini Palli
    72 views3 pages
    This 40-50 hour machine learning and deep learning course costs 25,000 rupees. The course provides an introduction to fundamental machine learning and deep learning concepts, algorithms, and hands-on practice in Python. Key topics include supervised and unsupervised learning, neural networks, convolutional neural networks, and applications in image processing, natural language processing and more. Regular attendance and participation are required along with practice on a laptop or desktop. Upon completing the course, students should understand a variety of algorithms and be able to apply machine learning to real-world problems.

    Original Title

    ML and Deep learning syllabus

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This 40-50 hour machine learning and deep learning course costs 25,000 rupees. The course provides an introduction to fundamental machine learning and deep learning concepts, algorithms, and hands-on practice in Python. Key topics include supervised and unsupervised learning, neural networks, convolutional neural networks, and applications in image processing, natural language processing and more. Regular attendance and participation are required along with practice on a laptop or desktop. Upon completing the course, students should understand a variety of algorithms and be able to apply machine learning to real-world problems.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    72 views3 pages

    ML and Deep Learning Syllabus

    Uploaded by

    Padmini Palli
    This 40-50 hour machine learning and deep learning course costs 25,000 rupees. The course provides an introduction to fundamental machine learning and deep learning concepts, algorithms, and hands-on practice in Python. Key topics include supervised and unsupervised learning, neural networks, convolutional neural networks, and applications in image processing, natural language processing and more. Regular attendance and participation are required along with practice on a laptop or desktop. Upon completing the course, students should understand a variety of algorithms and be able to apply machine learning to real-world problems.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 3

    Course: Machine Learning and Deep Learning

    Duration: 40-50 Hours


    Course Fee: 25000/-
    Course Description
    Machine learning is a rapidly growing field in Computer science, to the extent that it
    became a very popular buzz word. It seems it is everywhere today - from self-driving cars
    to automatic cancerous tumours detection. Deep learning is a sub field in the world of
    Machine learning mainly based around neural networks - a conceptual model of the human
    brain that has been around for decades but is getting more and more attention in the last
    several years. Using this model, we are capable of achieving wonderful results in solving
    complex problems that were once out of our reach.
    Based on fundamental knowledge of computer science principles and skills,
    probability and statistics theory, and the theory and application of linear algebra. This
    course provides a broad introduction to machine learning and statistical pattern recognition
    and deep learning. In this course we will start our journey in the world of deep learning -
    we will start by getting familiar with basic concepts and theory, all the way down to actual
    hands-on practice.

    Course Requirements
    1. Regular class attendance is the main requirement of this course.
    2. Active class participation, this means you must spend some quality time preparing for
    your next class.
    3. Regular practice will be required using either laptop or desktop.

    Course Syllabus
    Machine Learning

     Introduction
     What is Machine Learning
     What is Artificial Intelligence (AI)
     Machine Learning vs AI
     Machine Learning vs Deep Learning
     Required Maths
    o Linear Algebra
    o Probability
     Probability distributions (Continuous and Discrete)
     Central Limit Theorem
    o Statistics
     Types of Machine Learning
    o Supervised
    o Unsupervised
    o Reinforcement
     Tool Kit
    o Python Basics
    o Numpy
    o Pandas
    o Matplotlib
    o Scikit-learn or sklearn Library
     Dimension Reductionality
    o Data Analysis Using Principal Component Analysis (PCA)
     Eigen values, Eigen vectors, Orthogonality
     For image
     For Iris Dataset
     Data Visualization
    o Concepts of Size, Shape, Color
    o Various Visualization types
    o Heat map
     Text processing to features
    o Sentence Splitting and Tokenization
    o Punctuations and Stop words
    o Lemmatization
    o Bag-of-words
     Supervised algorithms
    o Linear Regression
    o Logistic Regression
    o Decision Tree
    o Bagging
    o Random Forest
     Unsupervised algorithms
    o K means
    o Clustering
     Distance measures
     Different clustering methods (Distance, Density, Hierarchical)
     Feature Extraction and selection
     Bias-Variance
     Under fitting and over fitting
    Deep Learning
     Perceptrons: What is a Perceptron, XOR Gate
     Activation Functions
    o Sigmoid
    o ReLU, Hyperbolic Fns,
    o Softmax

     Artificial Neural Networks


    o Introduction
    o Perceptron Training Rule
    o Gradient Descent Rule

     Gradient Descent and Backpropagation


    o Gradient Descent
    o Stochastic Gradient Descent
    o Backpropagation
    o Overfitting
    o Cross Validation
    o Feature Selection
    o Regularization
    o Hyper parameters
    o Dropout
     Introduction to Convolutional Neural Networks:
    o Introduction to CNNs
    o Introduction to Recurrent Neural Networks (RNN)
     Deep Learning applications
    o Image Processing
    o Natural Language Processing
    o Speech Recognition
    o Video Analytics
     Tools
    o Tensor flow
    o Pytorch
     Sample projects
     Interview Questions

    Learning Outcomes
    By the end of the course, students should be able to:
     Develop an appreciation for what is involved in learning models from data.
     Understand a wide variety of learning algorithms.
     Understand how to evaluate models generated from data.
     Apply the algorithms to a real-world problem, optimize the models learned and report on
    the expected accuracy that can be achieved by applying the models.

    Name: Padmini
    Contact Number: 8500900654

    You might also like