Certification Course in AI and Machine Learning

  • Artificial intelligence (AI) is the simulation of human intelligence processes by machines, especially computer systems. These processes include learning (the acquisition of information and rules for using the information), reasoning (using rules to reach approximate or definite conclusions) and self-correction. Particular applications of AI include expert systems, speech recognition and machine vision.
  •  

Objectives

  • Certification course in AI & Machine Learning provides a broad introduction to artificial intelligence and machine learning, including data analysis and data visualization. The course will go into depth about supervised learning, unsupervised learning, reinforcement learning, and deep learning. Participants will have the opportunity to explore numerous AI and/or ML applications, which will enable them to apply learning algorithms for solving trending real-world problems such as autonomous driving, social media analytics, affect recognition, computer vision, medical informatics, and building interactive robots.
  •  

Course Modules

  1. 1. Foundations (20 Hours)
    • » Python
    • » Data Visualization and Analysis
    • » Statistics and Probability
    • » Linear Algebra
  2. 2. Fundamental Learning (52.5 Hours)
    • » Introduction to AI: Logic and Search
    • » Overview of ML: Training/Testing, Pipeline, Evaluation Metrics etc
    • » Practical Aspects of ML: Bias/Variance, Overfitting; Jackknifing/, Cross-Validation Occam's razor; Regularization and Model Selection
    • » Supervised ML: Bayes Classification, Regression, Least Square and GD Optimization, Decision trees, Ensembles, RDF, SVM and kernels
    • » Supervised ML: Perceptron, MLP, GD using Backpropagation, RBF, HMM
    • » Unsupervised ML: Clustering, Dimensionality Reduction (PCA/LDA, SVD) 1. 2.
  3. 3. Advance Learning (22.5 Hours)
    • » Reinforcement Learning: Q-Learning, SARSA, DQN, DDPG 4.5 3 4.5 3
    • » Deep Learning: CNN, Auto Encoder, RBM, RNN, GAN
  4. 4. Advance Learning Applications (33 Hours)
    • » Computer Vision Natural Language Processing Robotics and Autonomous Vehicles Explainable AI and Ethics
  5. 5. Advance Learning Capstone
    • » ML + Application Domains

Total No of Hours - 128 (Include lab hours)

Pedagogy

  • Case Study and capstone project under the guidance of a mentor.
  • Online Live Classes supplemented by Assignments/Quiz etc
  • Virtual labs by TAs (hand-selected PhD students)

Assesments

  • Assignment based evaluations - every fortnight.
  • Quizzes every month.
  • One end-sem examination.
  • Capstone project evaluation at the end of the semester.
  • A minimum of 70% attendance to the LIVE lectures is a prerequisite for the successful completion of this program. There may be periodic evaluations built in throughout the duration of the course. These may be in the form of a quiz, assignment or other objective/subjective assessments as relevant and applicable to the program and are designed to ensure continuous student engagement with the course and encourage learning. While the results/feedback on such assignments will be provided, no consolidated mark or grade sheets shall be distributed to the Participants at the end of the course.

For further details: Click here