Machine Learning & Deep Learning

Disciplined Agile for 2 days

Institute: IIM Kashipur
Programme Start Date: 26th November, 2022
Admission: Open
Batch Number: 01
Deadline To Apply: 22nd November, 2022
Programme Type: D2D
Class Timings: Saturday – 09:00 a.m. to 12:00 p.m.

Course Overview

Synopsis

Did you know that Machine Learning (ML) and Deep Learning (DL) are the two main pillars of Data Science and are subsets of Artificial Intelligence? With these evolving tech elements, businesses can actually take home valuable outcomes from the vast world of data science. Organisations need to understand that innovation is the only way forward.

Programme Overview

IIM Kashipur’s Post Graduate Certificate Programme in Machine Learning & Deep Learning (PGCPMLDL) is designed to introduce and demonstrate machine learning and deep learning concepts in various business applications. This programme will use open-source platform Python to demonstrate and help participants learn the new tech components. This advanced one-year programme is intended to equip the participants with a clear understanding and differentiation between AI and ML concepts frequently used in the industry.

mldl-overview

Programme Highlights

  • Contextually designed 12-month programme for working professionals
  • Campus immersion module of 4 days
  • Taught using the open-source platform – Python

Programme Details

Pedagogy

The programme will be taught using Python machine learning and deep learning libraries. Libraries/packages that will be used in the programme are numpy, pandas, matplotlib, scikit-learn, tensorflow, keras, and nltk, among others. Participants would be completing assignments, quizzes, and a capstone project.

Key Learning Outcomes

  • Equip learners with a clear understanding of AI and ML concepts
  • Familiarise students with advanced ML and DL programming, tools, and techniques
  • Demonstrate how ML and DL can be applied in to resolve business problems
  • Upskill or transition successfully into the field of data science

Programme Delivery

There will be a mix of online sessions (129 hours) and on-campus sessions (24 hours). The online sessions will be conducted via a state-of-the-art Interactive Learning (IL) platform and delivered in Direct-to-Device (D2D) mode that can be accessed by learners on their Desktop, Laptop, Tablet or Smartphone.

Campus Immersion

There will be 4 days of campus immersion at IIM Kashipur.
The in-campus modules are subject to the conditions that prevail at that point of time. These conditions pertain to the pandemic or other unavoidable reasons. In case the on-campus module is not confirmed due to COVID-19 situation, the same will be included in the total number of online sessions.

Who Should Attend?

  • This programme is ideal for Engineers, Marketing & Sales Professionals, Domain Experts, and Software & IT Professionals.
  • The programme is meant for business and data analysts and mid-stage professionals looking to upskill or transition into the field of data science.
  • Professionals with a background in mathematics, statistics, and engineering are preferred.

Eligibility Criteria

  • Bachelor’s Degree or equivalent (10+2+3 or 10+2+4)/two Years Master’s Degree or Equivalent from a recognised university (UGC/AICTE/DEC/AIU/State Government) in any discipline.
  • Work experience of at least TWO years is preferable after completion of the qualifying education.
  • Prior knowledge of Statistics and Mathematics at the high school level is preferred.
  • Participants who fulfil the above criteria but are not working currently are also eligible for the programme.
    *Internships and Trainee experiences are not considered as Full-time work experience

Admission Criteria

Admission will be based on the overall profile of the applicants.

Assessment and Certification

Evaluation

Performance of participants will be monitored on a continuous basis through quizzes, assignments, tests and examinations. The participant is required to score minimum marks/grades as decided by the Institute from time to time to complete the course. The evaluations are designed to ensure continuous student engagement with the course and encourage practical learning. Students who successfully clear the same along with the requisite attendance criteria will be awarded a Certificate from IIM Kashipur as appropriate.
Qualifying criteria for assessments: 60%

Attendance Criteria

A minimum of 75% attendance is a prerequisite for the successful completion of the programme.

Certification & Alumni Status

  • Participants who successfully meet the evaluation criteria and satisfy the requisite attendance criteria, will be awarded a ‘Certificate of Completion’.
  • Participants who are unable to clear the evaluation criteria but have the requisite attendance will be awarded a ‘Certificate of Participation.
  • Participants will be accorded with IIM Kashipur alumni status

Sample Certificate

*The certificate shown above is for illustration purposes only and may not be an exact prototype of the actual certificate. ** IIM Kashipur reserves the right to change the certificate and specifications at any time without notice

IIM-K-MLDL-1
IIM-K-MLDL-2

Date & Fees

Programme Fee

ParticularsAmount (in ) *
Registration Fee6,100
Processing Fee** (Collected at the time of application)10,000
Programme Fee1,63,000
Campus Fee32,000
Alumni Fee (Optional)10,000
Total Fee (Excl. Registration Fee)2,05,000
Note:
  • *Taxes will be added as applicable
  • ** Processing fee contains INR 6,100/- towards Registration fee & INR 3,900/- towards the programme fees.
  • ***Processing fee of INR 7,500/- is refundable in case the participant’s profile is rejected by IIM Kashipur.
    This is with reference to the refund of the Processing Fees, please note that the Processing Fee shall not be refunded in the following circumstances:
  • i. In case candidate rejects the offer issued by the Institute; and
  • ii. In case the application is rejected due to submission of incomplete documents and/or providing incomplete information and/or eligibility criteria not fulfilled
    **In case the Applicant’s profile is rejected by the Institute then the initial amount paid on registration shall be refunded subject to a deduction of ₹2,500/- by way of administrative charges.

Instalment Schedule

Instalment I II III IV
DateAt the time of applicationWithin one week of offer rollout10th January 202310th April,
2023
10th July,
2023
Amount (in ₹)*3,900 52,00052,00052,00045,100

*GST will be additional as applicable.

Important Dates

Application Closure29th August 2022
Induction Date1st October 2022
End of programme (Last session including assessment)October 2023

Programme Content

1
Overview
  • SessionTopics CONCEPTUAL FOUNDATIONS1Introduction to Machine Learning and Deep LearningIntroduction to AI
  • Branches of AI
  • AI and Machine Learning
  • AI and Deep Learning
  • ML and DL Applications for Business
  • 2Mathematical Foundations for Machine Learning and Deep LearningLinear Algebra
  • Calculus
  • 3Statistical FoundationsConcepts of Probability
  • Distributions
  • MACHINE LEARNING FOUNDATIONS4-6Introduction to PythonBasics of Python Programming
  • Operators and Expressions
  • Decision Statements
  • Loop Control Statements
  • Functions & Python Packages
  • Working with Files
  • Object Oriented Concepts
  • VISUAL EXPLORATORY & DESCRIPTIVE ANALYTICS7-9Descriptive AnalyticsDescriptive Statistics
  • Data and Distributions
  • Visual Exploratory Analytics
  • INFERENTIAL ANALYTICS10-11Foundations of Inferential AnalyticsInferential Statistics and Hypothesis Testing

 AUTOMATED DATA COLLECTION12-13Automated Data Collection Using PythonPREDICTIVE ANALYTICS

SUPERVISED MACHINE LEARNING – REGRESSION14-16Business Context: Prediction

  • Machine Learning Context: Linear RegressionSimple Linear Regression
  • Multiple Regression
  • Regression Diagnostics
  • Regularization Methods – LASSO, RIDGE, ELNET

TIME SERIES FORECASTING17-18Business Context: Forecasting

  • Machine Learning Context: ForecastingTime Series Regression

19-20Business Context: Prediction

  • Machine Learning Context: RegressionModelling non-linear relationships

SUPERVISED MACHINE LEARNING- CLASSIFICATION21-23Business Context: Prediction

  • Machine Learning Context: ClassificationClassification Basics
  • Logistic regression, N-Bayes, Decision Trees, KNN, Support Vector Machines
  • Confusion Matrix
  • Cost-Benefit Analysis

ADVANCED MACHINE LEARNING TECHNIQUES24-25Business Context : Prediction

  • Machine Learning Context: Ensemble MethodsEnsemble Methods
  • Random Forests
  • Bagging
  • Boosting

UNSUPERVISED MACHINE LEARNING26-28Business Context: Segmentation

  • Machine Learning Context: ClusteringClustering Basics
  • k-means, hierarchical and dbscan clustering
  • Clustering diagnostics

RECOMMENATION SYSTEMS29-30Business Context: Market Basket Analysis & Recommendations

  • Machine Learning Context: Recommender SystemConcepts of Market Basket Analysis
  • Association rule mining
  • Introduction to Collaborative Filtering
  • DEEP LEARNING – FOUNDATIONS31-32Deep Learning IntroductionData Concept of Learning
  • Comparison Machine Learning
  • Data Representation

Introduction to Tensors


  • Tensors as data containers
  • Basic Tensor Operations
  • Types of Tensors
  • Tensors for Practice
  • DEEP LEARNING – ARCHITECTUTRE & APPLICATIONS33-34Network ArchitectureOptimizers, Loss Functions, Activation Functions

Deep Learning for Regression


  • Dense Layer Architecture and Use-Case for Regression

Deep Learning for Classification


  • Dense Layer Architecture and Use-Case for Classification
  • DEEP LEARNING- RECURRENT NEURAL NETWORKS35-36Recurrent Neural NetworksIntroduction to RNN
  • Comparison with Dense Layer Architecture
  • Application of RNNs for sequence data
  • Popular types of RNN (LSTM and BiLSTM)
  • Recurrent Neural NetworksRNN for Uni-variate Data
  • RNN for Multivariate Data
  • RNN Optimization
  • DEEP LEARNING- CONVOLUTIONAL NEURAL NETWORKS- COMPUTER VISION37-38Convolutional Neural NetworksIntroduction to CNN
  • Comparison with Dense Layer Architecture
  • Convnet architecture – Layers
  • Convnet architecture – Pre-processing
  • Convolutional Neural NetworksConvnet architecture – Data Augmentation
  • Convnet architecture – Fine Tuning
  • CNNs using pre-trained model
  • Visualizing convnet learning

TEXT ANALYTICS USING MACHINE LEARNING & DEEP LEARNING39-40Business Context: Learning from Text Data

  • Machine Learning Context: Text AnalyticsIntroduction to Text Analytics Process & Applications
  • NLTK, scikit-learn
  • Building & Managing Corpus
  • Data Wrangling and Text Pre-Processing
  • Text Vectorization'
  • a.BoW Model
  • b.One-hot encoding
  • c.Frequency Vector
  • d.TF-IDF
  • e.Word Embeddings

Business Context: Text Analytics Application

  • Machine Learning Context: Supervised LearningText Classification
  • Sentiment Analysis

Machine Learning Context: Unsupervised Learning


  • Topic Modelling
  • Sentiment Analysis
  • WEB-SERVICES FOR MACHINE LEARNING41-42Web-services for Machine LearningETHICAL ISSUES AND GOVERNANCE IN AI43Ethical Issues and Governance in AIGENERATIVE ADVERSARIAL NETWORKS44-45Introduction to GANArchitecture
  • Generator Network
  • Discriminator Model
  • Adversarial Network
  • Setting up and Training GAN
  • REINFORCEMENT LEARNING46-47Introduction to RLOverview of Environments in RL
  • Formulation of problems in RL
  • Q-learning methods for RL
  • Applications using RL

CAPSTONE PROJECT48-49Student Project Presentations50-51Student Project Presentations

Be the first to add a review.

Please, login to leave a review
Add to Wishlist
Duration: 12 Months
Lectures: 1

Talk to Our Experts














    Please prove you are human by selecting the Car.