Machine Learning From Theory to Modelling in Python (Cohort 3)

In this course you will learn the fundamentals of Machine Learning including intuitions, important theoretical aspects (without going deep into Mathematics) and how to use machine learning algorithms to solve problems. Students will learn about the foundational underpinnings of machine learning as well as how to put that knowledge to the test with practical exercises.

The course takes unique project focused approach to teach you machine learning by building machine learning models. The instructor will walk you through a series of curated projects, and explain the key concepts as they arise. Students will learn the theory and how these models work under the hood while writing code.

The course balances learning theory, coding exercises, and working on projects. Students who take this course will be able to:

  • Identify and frame problems that can be solved by machine learning
  • Choose the right techniques to the problems
  • Understand key machine learning concepts and how algorithms / models work
  • Identify and fix problems with messy datasets
  • Build and training various models with sklearn
  • Troubleshoot and improve models
  • Discuss the parts and processes involved in building large scale machine learning applications
    • Session 1: Nov 23rd 2pm-4pm PST (US Pacific Time, GMT-8)
    • Session 2: Nov 25th 2pm-4pm PST
    • Session 3: Nov 30th 2pm-4pm PST
    • Session 4: Dec 2nd 2pm-4pm PST
    • Session 5: Dec 7th 2pm-4pm PST
    • Session 6: Dec 9th 2pm-4pm PST
    • Session 7: Dec 14th 2pm-4pm PST
    • Session 8: Dec 16th 2pm-4pm PST

    • 4 weeks / 8 sessions / 16 hours
    • 8 lectures / 4 hands-on code labs
    • Capstone project, Github portfolio
    • Live Sessions (with zoom), Real time interaction
    • Slack support in and after class
    • 1-year access to course materials

    Check the content tab for full course outlines.

    Developers, data scientists, students.

  • Basic familiarity with python
  • Using Jupyter Notebook or Colab
  • Difficulty Level
    Est. time spend per week: 4 hours live class (required) + 2 hours homework (required) + 2 hours projects (bonus, optional).

    Full refund upon request before the first session ends (Nov 23rd, 2020 4:00pm PST). 5% transaction fee is not refundable.

    If missed live sessions, you can watch recordings any time, along with interactive learning tools, slides, course notes
    Students have life time access to course materials

  • Earn Certificate of Completion
  • Financial aid is available for application, contact for details
  • Previous Cohorts:
  • Cohort 2: Mar 23 ~ Apr 9, 2020
  • Cohort 1: Jan 15 ~ Jan 31, 2020
  • Module 1: Machine Learning fundamentals
    • Introduction to machine learning and its industrial applications
    • Review on machine learning programming (pandas, sklearn, etc.)
    • Jupyter and Colab notebooks versus Pycharm
    • H​omework: ​practice exercise on python and related libraries

    Module 2: Machine Learning Algorithms
    • Linear regression (theory and practice)
    • Logistic regression for classification (theory and practice)
    • k-NN for classification
    • Introduction to Bayesian statistics + Naive Bayes for classification
    • H​omework: ​practice exercise on classification using k-NN, Logistic Regression and Naive Bayes and comparison of their performances in different examples

    Module 3: Regularization
    • Why do we need regularization?
    • Different types of regularization
    • Regularization in practice (regression and classification)
    • H​omework: ​practice exercise on regularization using Lasso and ElasticNet

    Module 4: Ensemble learning
    • Introduction to ensemble learning
    • From decision trees to random forests
    • Gradient boosting
    • Adaboost
    • H​omework: practice exercise on random forest and Adaboost for classificationtasks

    Module 5: Feature Engineering
    • How to build and hyper-parameter tune KNN for Binary Classification in the cloud
    • Linear and nonlinear dimensionality reductions
    • Dimension reduction for features extraction
    • Dimension reduction for visualization
    • H​omework: ​practice exercise on dimensionality reduction using PCA, ICA,t-SNE and UMAP

    Module 6: Clustering
    • Hierarchical clustering
    • Partition based clustering and k-means
    • Affinity propagation
    • H​omework: ​practice exercise on clustering using k-means as well as implementation of hierarchical clustering and affinity propagation on some example dataset

    Module 7: Reporting results and preparation for interview
    • Proper visualization in machine learning
    • Performance report in machine learning era
    • Common interview questions in data science and machine learning

    Module 8: Project overview
    What the attendees will learn:
    • Kickstart on deep learning
    • Introducing the course project
    • Project implementation in class
    • Q&A about the project and implementation
    Ali & Farnoosh

    Ali is the lead of machine learning at Cyclica Inc and leads the team to further improve technology for predicting interaction between ligands and target proteins. As a computational biologist and machine learning specialist, Ali has worked on a series of scientific articles in high impact scientific journals and international conferences covering such fields as transfer learning, dimensionality reduction and unsupervised clustering. He earned a Ph.D degree from the University of Toronto, and a master of a mathematics degree from the University of Waterloo.

    Farnoosh Khodakarami
    Farnoosh is a computer scientist with more than 10 years background in machine learning, software development, and algorithm design. She has also extensive research and teaching experience in different subjects of computer science
    (226 Ratings)

    Student Feedback


    the coding exercises are very effective to help me learn. comparing and selecting methods and rationale behind tuning of hyperparameters (Class 20200323)

    handsout and lecturs to explain complex concepts easily understand. The instructor did a very good job explaining some fairly difficult concepts at an appropriate level, and answered questions thoroughly and clearly (Class 20200323)

    enjoy the Q&A and real interaction with instructors in the sessions (Class 20200323)

    classes were well done and the overview was often insightful (Class 20200323)

    enjoy learning about dimension reduction methods and clustering methods in this course (Class 20200323)

    Good class examples and assignements reinforced the couse material very well. (Class 20200115)

    The instructor explained the content in a very effective way. (Class 20200115)

    Seeing the complete process from beginning to end within an accessible environment. The course did a few examples. I would pay again for 5 more examples, especially business (fin, fraud, ecommerce, customer segmentation) and marketing data examples. (Class 20200115)

    For the 'homework', I think a short lab-type exercise with some scaffolding and a clear purpose would have been better than an instruction for us to just go out and find a dataset to try it on. (Class 20200115)

    • Start Date: Nov 23, 14:00PST | Mon,Wed
    • Venue: Online (zoom)
    • Fee:
      $299 $299 USD
    • Max/Avail. Seats 25/3
    • Status: live now
    • Course Preview:

    • Course Sample:

    • Any questions? Contact Us
    Enroll this course