Women In Tech Event - Deep Learning Talk: Convolutional Neural Networks

Thursday, January 18, 2018 - 18:00
NYC Women in Machine Learning & Data Science
New York

Our meetup group is open to all women and men who support our cause. However, in support of our mission, priority for this event will be given to women and non-binary members. Our Code of Conduct is available online and applies to all our spaces, both online and off.
https://github.com/WiMLDS/starter-kit/wiki/Code-of-conduct ---

This is an intermediate level deep learning talk. We will focus on Convolutional Neural networks (CNNs) using Python and pyTorch. First we will review the components of a CNN and discuss why these networks work so well for computer vision tasks. Then we will compare two styles of CNN implemented in pyTorch on CIFAR10; a VGG-like network [1] and a Residual Network. [2]

This event assumes a basic understanding of neural networks, backpropagation, and neural network training through stochastic gradient descent.

Topics covered:
- Introduction to convolutional neural networks
- Motivation and biological inspiration
- Kernels
- Padding, stride
- Walk through of a basic CNN in pytorch
- Comparison of a VGG-like and Residual Network architecture on CIFAR 10 in pytorch Reading Preparation (optional)
No preparation is required but if you do not have any background on neural networks then here are a few resources Slides:
WiMLDS Deep Learning Workshop
Intro to Neural Nets (1 - 1.5 hour read) https://learningmachinelearning.org/2016/07/26/introduction-to-neural-networks/
Regularization (30 min read)
Neural Networks and Deep Learning book by Michael Nielsen
20 hours of videos from the Bay Area Deep Learning School
Day 1: https://www.youtube.com/watch?v=eyovmAtoUx0
55 minute deep learning intro (if you have access to safari) https://www.safaribooksonline.com/library/view/introduction-to-deep/9781491999608/
Here is a great whistle stop tour.

About the Speaker

Laura Graesser is studying for an MS in computer science at NYU, focusing on machine learning. Laura is particularly interested in neural networks and their application to computer vision, NLP and reinforcement learning. Most recently, Laura is interested in combining reinforcement learning with supervised learning, knowledge distillation, and in tackling multi-modal and multi-task learning.

In her spare time, Laura enjoys dancing, listening to jazz, going to art exhibitions, and writing about machine learning. Twitter: @lgraesser3
Github: lgraesser
LinkedIn: Laura Graesser

• What to bring

• Important to know