Certification program in Machine Learning & Deep Learning

Program Description and Objectives

Machine Learning (ML) and Deep Learning have been subjects of study since the inception of neural networks. With advancement in technology, especially, Graphical Processing Units (GPUs), the demand for knowledgeable and skilled personnel in this area has received a fillip. Applications of ML & Deep Learning range from Computer Vision to Speech recognition & translation to marketing and to drug discovery. It is one of the fastest growing fields of Artificial Intelligence. The objectives of the present program are:

  • To work on important technologies of ML & AI: Deep Learning, Natural Language Processing and Reinforcement Learning.
  • Developing skills in predictive analytics using ML and Deep Learning algorithms.
  • Practical implementation of every technique with real world applications.

Who should attend

The course is especially designed for executives from industry, students, faculty, and research scholars who are interested in understanding the concepts and practical applications of Machine Learning, Deep learning and Artificial Intelligence. A simple programming background would be preferable.


We are keenly aware that our participants come from varied backgrounds—both college wise and basic-education-wise. We strongly believe that a course in data analytics can only be practice-based rather than theory based. We also believe that a practice based course requires constant interaction with the teacher during lecture hours in real time. As it is an online course, the teaching pedagogy is like this: First, the theory part is conceptually explained without getting into mathematics and then a project is undertaken to implement the techniques. Datasets for implementation are made available in advance and so a copy of code (or hints on it) that we need to execute. The code is numbered and copiously commented so that long after the lecture has finished, students can go back through the code/comments and refresh their knowledge. During the lecture, we execute this code (or prompt students to fill in the gaps), line-by-line and explain the steps. At his end, the student executes the required code on his laptop. Consequently, results are available at our end as also with the Students immediately. In short, both the teacher and students are working on their respective laptops simultaneously; students solve their problems and ask any questions to clarify. The whole experience is just as if everyone is sitting in a laboratory and working together. Our e-learning platform has a wealth of material and articles reflecting latest developments in this field; it is frequently updated. Students are assured of continued access to e-learning site even after the program has finished.

Program Duration: 71 Hours

Class Timing

Saturday - 02:00 PM to 05:00 PM (from 30th March to April End)

Sunday - 03:00 PM to 05:00 PM (May ?ll the end of the course)

Program Delivery

The sessions will be delivered on Education Lanes(TMGFL) platform through Direct to Desktop mode.

Total Fees

Course Fees are payable by Student directly to Tech Mahindra Growth Factories Limited

Course Fee :

Rs. 40,000/- + GST (Lump sum Payment Discount of INR 5,000/- to be given to all participant joining this course)

Other Fee :

Rs. 5,000/- + GST : E-resources/Virtual Machine containing learning ecosystems & Software’s(Mandatory Fees)

Collection of Fee:

Program Fees (Part A)
Installment Schedule Registration Fees Admission Fees 1st Installment
Installment Amount 10,000/- + GST 15,000/- + GST 15,000/-+ GST
Installment Date At the time of Enrollment Mar 19 Jun 19
Other Fees (Part B )
E-resources/Virtual Machine containing learning ecosystems & Software’s (Mandatory Fees) Rs 5,000/- + GST per participant Payable directly to FORE School of Management, New Delhi.

Program Content

  • Data Exploration
    Learning Python and Data Exploration
    1. Familiarity with numpy pandas
    2. Data Visualization using Matplotlib and seaborn
  • Unsupervised Learning
    1. Kmeans
    2. Hierarchical (with text clustering)
  • Supervised Learning
    1. Decision trees
    2. Ensemble Modeling
      • Random Forests
      • Gradient Boosting Machines
      • Xgboost
      • LightGBM
    3. Dimensionality Reduction: PCA
    1. Projects using above algorithms will be worked out and will involve a) Feature Engineering & Feature Transformations; b) Model Performance Evaluation using various metrics such as Accuracy; Precision/Recall; kappa; ROC/AUC; and c) In one case the project work will involve Balancing unbalanced data with emphasis on outlier detection. Concept of Bias-Variance tradeoff and regularization will be explained.
    2. Experiments would use Scikit-learn libraries and H2o among others
  • Deep Learning
    Up and running with tensorflow:
    1. Computational graphs in tensorflow
    2. Linear Regression with tensorflow
    3. Implementing Gradient Descent
    4. Machine Learning with tensorflow
    Simple and Multilayer Neural Networks:
    1. Experiments using keras
    2. Experiments using H2O
    Introduction to and working with Autoencoders:
    1. Stacked Autoencoders
    2. Denoising Autoencoders
    3. Variational Autoencoders
    4. Generating images/digits using Variational Autoencoders
    5. Keras and H2O would be used in developing Autoencoders
    Convolutional Neural Networks:
    1. Review of the components of Convolution Neural Networks
    2. Avoiding over-fitting and under-fitting
    3. Techniques of algorithm optimization
    4. Experiments would be conducted using keras sequential model as also with keras functional model.
    Data Augmentation and image processing for better modelling
    Deep Learning for tabular data (or for DataFrames)
    Very Deep Convolutional Neural Network: Transfer Learning:
    1. Using ResNet
    2. Using VGG16
    Recurrent Neural Networks (LSTM)
    1. Processing Sensor data
    2. Processing sequential and time-series data
    Natural Language Processing:
    1. Bag of Words representation
    2. Word2Vec representation
    3. Classification using RNN & Deep Learning
  • Reinforcement Learning
    Reinforcement Learning:
    1. Policy Search
    2. Open AI Gym
    3. Policy Gradients
    Reinforcement Learning:
    1. Q-learning, and
    2. Deep-Q Learning

Detailed Course Content may please be seen here.

Assessments: Based on Performance in Exercises & Projects

Tech Mahindra Growthd Factories Ltd.

A - 20, Sector - 60, Noida - 201301


Mobile:+ 91 9975806184

Apply Now



Request Info

Feel free to ask