- 123 (Registered)
Description / Overview of the Course
How can artificial systems learn from examples, and discover information buried in massive datasets? We explore the theory and practice of statistical machine learning, focusing on computational methods for supervised and unsupervised data analysis. Specific topics include Bayesian and maximum likelihood parameter estimation, regularization and sparsity-promoting priors, kernel methods, the expectation maximization algorithm, and models for data with temporal or hierarchical structure. Applications to regression, categorization, clustering, and dimensionality reduction problems are illustrated by examples from vision, language, bioinformatics, and information retrieval.
Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. Many researchers also think it is the best way to make progress towards human-level AI. In this class, you will learn about the most effective machine learning techniques, and gain practice implementing them and getting them to work for yourself. More importantly, you’ll learn about not only the theoretical underpinnings of learning, but also gain the practical know-how needed to quickly and powerfully apply these techniques to new problems. Finally, you’ll learn about some of Silicon Valley’s best practices in innovation as it pertains to machine learning and AI.
This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI). The course will also draw from numerous case studies and applications, so that you’ll also learn how to apply learning algorithms to building smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas.
In this course, you practice with real-life examples of Machine learning and see how it affects society in ways you may not have guessed!
Being an advanced course students should be comfortable with basic multivariable calculus, should have understanding of programming fundamentals. Knowledge of Python will be helpful.
This course is also for individuals who are passionate about the field of data science and who are aspiring to apply machine learning in their business, industry or research.
Why Should i do this Course ?
Machine Learning has become the hottest computer science topic of 21st century. All big giants such as Google, Microsoft, Apple, Amazon are working on ML projects and research organizations such as NASA, ISRO invest heavily in R&D for ML projects.
Machine Learning in the News
- A.I. Researchers Are Making More Than $1 Million, Even at a Nonprofit
- At Mars, Jeff Bezos Hosted Roboticists, Astronauts, Other Brainiacs and Me
- Shake-up at Facebook highlights tension in race for AI
Class Breakdown – Topics
Introduction To Machine Learning
- Introduction to Machine Learning
- Python 3.5 overview
- Linear Algebra
- Statistics and Probability
- Numpy, Scipy, and Scientific computation with Python
- Nearest Neighbour search and K-means clustering.
- Decision trees and Naive Bayes.
- Data Scraping, Handling, Cleaning
- Random Forest Classifiers.
Features & Dimentions
- Features and Importance
- Feature scaling
- The Curse of Dimensionality
- SVD and Principal Component Analysis
- Regression Techniques
- Numerical Optimization
- Introduction to Neural Networks
- Neural Architectures and Training
- Deep learning methods
- Convolutions and the GoogLe Net
- Dimensions revisited: The Auto-encoder
- Recurrent and Combined Architectures
- Support Vector Machines
- Introduction to Unsupervised and Reinforcement Learning
- Transfer Learning
Students will get hands on knowledge of what you have learned so far by building your own projects that use the techniques taught in this course to solve a real life problem.You will submit a report for evaluation.
- Handwritten digit classification
- Face Recognition
- Image classification and Object detection
- Automated music generation
- Text/Poem generating bot
- Recommender systems
- Emotion/Sentiment Analysis
Curriculum is empty
- 46 hours on-demand video
- 16 Articles
- 39 Supplemental Resources
- Full lifetime access
- Language: English
- Certificate of Completion