MIST101-2: How Does a Machine Learn?

2020/2021: 1 | 2 | 3 | 4 | 5


Image of MIST101-2

Have you ever wondered how machines learn and perform those seemingly magical tasks? In this workshop, we’ll explain the various modes of learning through which machines ‘learn’. We’ll dive into the analytical and technical aspects of machine learning and learn these methods in a fun-laden manner. In this workshop, we bring you the opportunity to build a machine learning model using the KNN algorithm and get your hands dirty while coding in Python.

Last but not the least, we have organised a contest where you can apply the concepts you have learned and challenge yourself to explore the world of ML even further! And did we forget to mention that we are partnering with Amazon Prime Student to provide gift cards worth 25 CAD each, when you answer them correctly* ! The workshop will be uploaded on October 1st, 2020 so don’t forget to add the date to your calendars!

Wait a minute, what time is it?…. We value the fact that you are busy, and hence we’ll upload the recorded videos on our YouTube channel, so that you can watch it when you have time!

Presentation slides are here and the Collab notebook can be found here.

Event Details

Topics to be covered:

  1. The Goal of Machine Learning
  2. Terminologies used in Machine Learning
  3. Supervised Learning
  4. Unsupervised Learning
  5. Reinforcement Learning
  6. A coding demo implementing the KNN algorithm

How to join our contest:

  • Upload your answers on the Kaggle competition.
  • Take the screenshot of your score.
  • Write a short paragraph as your answer to the question, asked at the end of the demo.
  • Submit the screenshot and your answer, via email to qiyangyolanda[dot]chen[at]mail[dot]utoronto[dot]ca

We’ll contact you if you win!

References:

Card, D. (2017, July 05). The “black box” metaphor in machine learning. Retrieved September 30, 2020, from https://towardsdatascience.com/the-black-box-metaphor-in-machine-learning-4e57a3a1d2b0

Castrounis, A. (2016, January 27). Machine Learning: An In-Depth Guide. Retrieved September 30, 2020, from https://www.innoarchitech.com/blog/machine-learning-an-in-depth-non-technical-guide

Bronshtein, A. (2020, March 24). Train/Test Split and Cross Validation in Python. Retrieved September 30, 2020, from https://towardsdatascience.com/train-test-split-and-cross-validation-in-python-80b61beca4b6

Harrison, O. (2019, July 14). Machine Learning Basics with the K-Nearest Neighbors Algorithm. Retrieved September 30, 2020, from https://towardsdatascience.com/machine-learning-basics-with-the-k-nearest-neighbors-algorithm-6a6e71d01761

Srivastava, T. (2020, April 01). K Nearest Neighbor: KNN Algorithm: KNN in Python & R. Retrieved September 30, 2020, from https://www.analyticsvidhya.com/blog/2018/03/introduction-k-neighbours-algorithm-clustering/

Tata, V. (2019, July 21). Simple Image Classification using Convolutional Neural Network - Deep Learning in python. Retrieved September 30, 2020, from https://becominghuman.ai/building-an-image-classifier-using-deep-learning-in-python-totally-from-a-beginners-perspective-be8dbaf22dd8

* Two amazon gift cards worth 25$ each will be provided to the top two submissions.