Get updates on Eligibility, Admission, Placements Fees Structure
Quick Facts
| Medium Of Instructions | Mode Of Learning | Mode Of Delivery |
|---|---|---|
| English | Self Study, Virtual Classroom | Video and Text Based |
Course Overview
With machine learning and artificial intelligence gaining immense popularity, the skills of future-ready analysts, engineers, technologists, and data managers also must expand, shift, and advance. Machine Learning: Fundamentals and Algorithms online course will provide you with ample technical knowledge and analytical methods to prepare you for the next gen of innovation.
Organised around 10 modules, the Machine Learning: Fundamentals and Algorithms course help you deepen and broaden your Python programming skills for ML applications. You can further apply this technical knowledge to the industry verticals currently integrating machine learning and AI into their digital drivers.
The Machine Learning: Fundamentals and Algorithms programme is designed for participants with Python programming experience who want to learn more about the underlying mathematics. Upon programme completion, you will receive a verified digital certificate from Carnegie Mellon University.
The Highlights
- Python Coding Exercise in Each Module
- Dedicated Programme Support Team
- Bite-Sized Learning
- Peer Discussions
- Mobile Learning App
- Knowledge Checks
- Offered by Carnegie Mellon University
- 10-week online programme
Programme Offerings
- Bite-sized Learning
- 10-week online course
- Coding exercises
- Mobile Learning App
- Support team
- Peer discussions
- Knowledge checks
Courses and Certificate Fees
| Certificate Availability | Certificate Providing Authority |
|---|---|
| yes | CMU School of Computer Science, Pittsburgh |
- Paying the Machine Learning: Fundamentals and Algorithms course fee is mandatory.
- A referral discount is available.
- A 10% group discount is also available.
Machine Learning: Fundamentals and Algorithms fee structure
Course | Fees in USD |
Machine Learning: Fundamentals and Algorithms | $2,500 |
Eligibility Criteria
To enrol in the Machine Learning: Fundamentals and Algorithms training, you must possess high-school-level proficiency in linear algebra, probability, calculus, statistics, and Python programming.
A certificate of completion will be offered when you complete the course.
What you will learn
By the end of the Machine Learning Fundamentals and Algorithms syllabus, you will be able to:
- Synthesise components of machine learning to build functional tools for the prediction of unseen data
- Apply concepts from statistics, linear algebra, probability, optimisation, and calculus to refine and describe the workings of machine learning algorithms
- Analyse and implement learning algorithms for regression, classification, and clustering
Who it is for
The Machine Learning: Fundamentals and Algorithms course are ideal for:
- Engineers - Design Engineers, Automation Engineers, Software Developers, Software Engineers
- Data Analytics Professionals - Data Scientists, Data Analysts, Analysts, Business Analysts
- Technical Managers/Directors - Directors of Business Systems & Information Technology, VP Analytics, Technology Director, Senior Engineer, Senior Developers, Tech Leads, VP Engineering, Director of Customer Experience, and many more
Admission Details
- To commence the enrolment procedure for the Machine Learning: Fundamentals and Algorithms programme, visit the programme website - https://execonline.cs.cmu.edu/machine-learning
- Once you’re on the website, hit the “Apply Now” button on the top.
- Log in using your credentials, or create a new account.
- Fill and submit the application form.
- Complete the fee transaction.
- Begin the course.
Application Details
During enrolment into the Machine Learning: Fundamentals and Algorithms programme, you have to fill an application form, which has fields like street address, full name, city, ZIP code, work experience, state, job title, company, profile, and industry.
The Syllabus
- Use a decision tree to make predictions
- Given labeled training examples, you will learn a decision tree.
- In machine learning, there are fundamental algorithms.
- Use the k-NN algorithm to classify points given a simple dataset
- Implement a full decision tree for learning and prediction.
- Employ model selection techniques to select k for the k-NN algorithm
- Implement a grid search to select multiple hyperparameters for a model.
- Creating machine learning solutions can require refinement of the inner workings of algorithms, including
- Adapting the k-NN algorithm for classification to regression
- Adapting decision trees for classification to regression, as well as
- Implementing learning for linear regression using gradient descent.
- Determine how convexity affects optimization
- Implement linear regression with optimization by stochastic gradient descent.
- Given i.i.d. data and parameters of a logistic regression distribution, compute conditional likelihood
- Implement stochastic gradient descent for binary logistic regression.
- Ways to combat overfitting
- Convert a nonlinear dataset to a linear dataset in higher dimensions
- Manipulate the hyperparameters of L1 and L2 regularization implementations
- Identify the effects on magnitude and sparsity of parameters.
- Combine simpler models as components to build up feed-forward neural network architectures
- Write mathematical expressions in scalar form defining a feed-forward neural network.
- Carry out the backpropagation algorithm on a simple computation graph over scalars
- Instantiate the backpropagation algorithm for a neural network.
- Explore solutions to practical challenges in this final module
- Implement the k-means algorithm and recognize
- Explain challenges in selecting the number of clusters.
Instructors
CMU School of Computer Science, Pittsburgh Frequently Asked Questions (FAQ's)
Matt Gormley and Patrick Virtue teach this course.
You will receive the certificate upon programme completion.
The course lasts for 10 weeks.
Yes, the course is also available on a mobile app to learn on the go.
You can download the course brochure if you want more information regarding the course.