Artificial Intelligence / Machine Learning / Deep Learning
COURSE OUTLINE:
This course will provide an excellent kick start in improving the level in AI/Machine Learning as a domain. The course is a well balanced between theory and hands-on lab, spread on real-world uses case studies. It will also offer a good foundation for Deep learning.COURSE OBJECTIVES:
Upon successful completion of this course, the participant will be able to:• Understand and analyze AI/ML opportunities, have balanced conversations with their clients on AI/ML topics.
• Identify and analyze different industry verticals for AI/ML problems by studying relevant Case studies (including UBER in NY, Netflix for content recommendations, TAG prediction and association for content, cancer diagnosis in healthcare, Malware detection in Microsoft dataset, Amazon fashion discovery engine, Chatbot concepts)
• Understand AI, ML, DL concepts and foundation for its algorithms.
• Start implementing algorithms in real world datasets
• Get the current industry status of Deep Learning
• Start thinking about how to automate things by relating to the case studies discussed in the sessions.
Pre-Requisites:
The participants should have basic knowledge of Python, Probability and Statistics. It is advised to refresh these skills to obtain maximum benefit from this workshop. If candidate don’t have any programming background, we will be covering Python fundamentals as we go along in the program. However, we also plan to offer two sessions ahead of the program (1: Python Basics and 2: Maths/Statistics Refresher), for those who want to formally brush up on these topics.
Upon successful completion of this course, the participant will:
- be able to understand and analyze AI/ML opportunities, have balanced conversations with your clients on AI/ML topics.
- Develop ability to understand/analyze different industry verticals for AI/ML problems by studying relevant Case studies (including UBER in NY, Netflix for content recommendations, TAG prediction and association for content, cancer diagnosis in healthcare, Malware detection in Microsoft dataset, Amazon fashion discovery engine, Chatbot concepts)
- Understand AI,ML, DL concepts and foundation for its algorithms.
- How to start implementing algorithms in real world datasets
- Get the current industry status of Deep Learning
- Start thinking about how to automate things by relating to the case studies discussed in the sessions.
Course Content
| Hour 0-3 | INTRODUCTION TO AI/ML ECOSYSTEMS AD AND MARKET DRIVERS |
|---|
| EXPLORATORY DATA ANALYSIS (EDA) |
| LINEAR ALGEBRA BASICS |
| Hour 4-10 |
| PROBABILITY AND STATISTICS |
| DIMENSIONALITY REDUCTION AND VISUALIZATION |
| PCA (PRINCIPAL COMPONENT ANALYSIS) |
| Hour 11-20 |
| (T-SNE)T-DISTRIBUTED STOCHASTIC NEIGHBOURHOOD EMBEDDING |
| REAL WORLD PROBLEM: PREDICT RATING GIVEN PRODUCT REVIEWS ON AMAZON |
| CLASSIFICATION AND REGRESSION MODELS: K-NEAREST NEIGHBORS |
| CLASSIFICATION ALGORITHMS IN VARIOUS SITUATIONSs |
| Hour 21-30 |
| PERFORMANCE MEASUREMENT OF MODELS |
| NAIVE BAYES |
| LOGISTICREGRESSION |
| LINEAR REGRESSION |
| SOLVING OPTIMIZATION PROBLEMS |
| QUICKCHECK ON LOGISTIC REGRESSION AND LINEAR REGRESSION |
| SUPPORT VECTOR MACHINES (SVM) |
| CASE STUDY 1: 1A) SURVIVAL PREDICTION IN TITANIC, 1B) TENNIS MATCH PREDICTION WIMBLEDON DATA SET |
| Hour 31-38 |
| DECISION TREES |
| FEATURIZATION AND FEATURE |
| UNSUPERVISED LEARNING/CLUSTERING |
| HIERARCHICAL CLUSTERING TECHNIQUE |
| DBSCAN (DENSITY BASED CLUSTERING) TECHNIQUE |
| RECOMMENDER SYSTEMS AND MATRIX FACTORIZATION |
| Hour 39-45 |
| CASE STUDY 2: PERSONALIZED CANCER DIAGNOSIS |
| CASE STUDY 3:TAXI DEMAND PREDICTION IN NEW YORK CITY |
| CASE STUDY 4: MICROSOFT MALWARE DETECTION |
| CASE STUDY 5:NETFLIX MOVIE RECOMMENDATION SYSTEM |
| CASE STUDY 6: STACKOVERFLOW TAG PREDICTOR |
| Hour 46-60 |
| CASE STUDY 7: QUORA QUESTION PAIR SIMILARITY PROBLEM |
| CASE STUDY 8: AMAZON FASHION DISCOVERY ENGINE |
| DEEP LEARNING:NEURAL NETWORKS |
| DEEP LEARNING: DEEP MULTI-LAYER PERCEPTRONS |
| DEEP LEARNING: TENSORFLOW AND KERAS. |
| DEEP LEARNING: CONVOLUTIONAL NEURAL NETS. |
| DEEP LEARNING: LONG SHORT-TERM MEMORY (LSTMS) |
| Hour 61-70 |
| Deep Dive in Deep Learning |
| AD-Click Prediction |
| Human Activity Recognition using smartphones |
| Song similarity and genre classification |
| Facebook Friend Recommendation using Graph Mi |
Corporate Trainer: Background And Experience Summary
- Technical expert and a passionate trainer having a keen interest in Research & Development, Technical Training and Project Management, have a proven work record of delivering more than 100+ workshops and Technical Training in various technologies at Corporate Companies
- Have been training students in various technical topics and core computer science subjects since 2012.
- Worked as technical consultant for Appolo and Wockhardt Hospitals. Worked for Oracle as a Software Engineer.
- Have been working with Vnurture Technologies in the areas of Corporate training and project consultancy.
- General Electric, Philips, Reserve Bank of India, Verizon (Yahoo), Sunlife Financial, Harman, Philips, JP Morgan, CGI, HP, Samsung, Accenture, National Payment Corporation of India, Bharat Electronics Limited, Brilio and in education institutes including IITs, NITs, Business Schools like Globsyn Crystals and other premier educational organizations.
- Delivered Data Science training for JP Morgan 2018
- Delivered Machine Learning and Deep Learning for CGI 2018
- Consulted Sun Life Financial for Deep Learning projects.
- Conducting Training on Applied AI for Verizon.
- Subject Matter Expert for Upgrade (Machine Learning program)
- Delivered training on AI and ML to General Electric 2018
- Delivered training for Applied AI via Python at BEL.
