MIST102-1: Convolutional Neural Networks

2020/2021: 1 | 2 | 3


Image of MIST102-1

Welcome to our MIST102 series. Previously, in our MIST101 series, you were introduced to various topics in machine learning. Ranging from supervised learning, KNN algorithm, artificial neural networks, overfitting, undercutting, regularizations, and ending with unsupervised learning and clustering. Now that you have set your foundation for machine learning let’s dive deeper into some more practical and useful applications of machine learning.

In this workshop, we introduce you to Convolutional Neural Networks (CNN). It’s a deep learning algorithm that takes in an image as an input and helps in many exciting tasks such as image classification, object detection, etc. This workshop will go over components of CNN, CNN architecture, data augmentation, 3D kernels as well give an introduction to 3D CNN implementations. This workshop also gives you an opportunity to work on your own mini project - A Car logo classifier.

Good News! We have made the process of participating and winning prizes a LOT simpler. After watching the workshop videos, you can test how well you have understood the concepts by participating in a short online quiz which consists of MCQs and short answer questions. This will not just help you reinforce what you have learned but also help you win prizes!

The quiz can be found here!

As always, we are partnering with Amazon Prime Student to provide gift cards worth 25 CAD each when you answer them correctly* ! So stay tuned for our upcoming workshop which will be released on our YouTube channel on January 23rd, 2021.

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!

Event Details

Topics to be covered:

  1. Components of CNN
  2. CNN Architecture
  3. Data Augmentation
  4. Intro to 3D kernels
  5. 3D CNN Implementations
  6. Demo: Mini project and Transfer learning

How to win prizes:

  • Participate in the quiz.
  • Answer the MCQs and short answer questions to the best of your knowledge.
  • Hit submit.
  • That’s it!

The quiz should take no longer than 10 minutes, provided that you have watched the videos!

We’ll contact you if you win!

References:

Techopedia, “What is a Pixel? - Definition from Techopedia,” Techopedia.com, 27-Feb-2012. [Online]. Available: https://www.techopedia.com/definition/24012/pixel. [Accessed: 27-Feb-2021].

“Box Blur Algorithm - With Python implementation,” GeeksforGeeks, 30-Dec-2020. [Online]. Available: https://www.geeksforgeeks.org/box-blur-algorithm-with-python-implementation/. [Accessed: 27-Feb-2021].

Sharpening an Image, 16-Jun-2005. [Online]. Available: https://northstar-www.dartmouth.edu/doc/idl/html_6.2/Sharpening_an_Image.html. [Accessed: 27-Feb-2021].

“Types of padding in convolution layer,” GeeksforGeeks, 15-Jan-2019. [Online]. Available: https://www.geeksforgeeks.org/types-of-padding-in-convolution-layer/. [Accessed: 27-Feb-2021].

Savyakhosla @savyakhosla, “CNN: Introduction to Pooling Layer,” GeeksforGeeks, 26-Aug-2019. [Online]. Available: https://www.geeksforgeeks.org/cnn-introduction-to-pooling-layer/. [Accessed: 27-Feb-2021].

Shubham, Shrutiparna, Vinita, and Vishal, “What is the difference between ‘SAME’ and ‘VALID’ padding in tf.nn.max_pool of tensorflow?,” Intellipaat, 02-Jun-2019. [Online]. Available: https://intellipaat.com/community/558/what-is-the-difference-between-same-and-valid-padding-in-tf-nn-maxpool-of-tensorflow. [Accessed: 27-Feb-2021].

“Data augmentation  :   TensorFlow Core,” TensorFlow. [Online]. Available: https://www.tensorflow.org/tutorials/images/data_augmentation. [Accessed: 27-Feb-2021].

P. Pai, “Data Augmentation Techniques in CNN using Tensorflow,” Medium, 03-Nov-2020. [Online]. Available: https://medium.com/ymedialabs-innovation/data-augmentation-techniques-in-cnn-using-tensorflow-371ae43d5be9. [Accessed: 27-Feb-2021].

J. Brownlee, “A Gentle Introduction to Transfer Learning for Deep Learning,” Machine Learning Mastery, 16-Sep-2019. [Online]. Available: https://machinelearningmastery.com/transfer-learning-for-deep-learning/. [Accessed: 27-Feb-2021].

P. Skalski, “Gentle Dive into Math Behind Convolutional Neural Networks,” Medium, 14-Apr-2019. [Online]. Available: https://towardsdatascience.com/gentle-dive-into-math-behind-convolutional-neural-networks-79a07dd44cf9. [Accessed: 27-Feb-2021].

* An Amazon gift card worth 25$ will be provided to the top submissions.