NPC Pune 2017

In this workshop on Image Classification using Deep Learning, we start from scratch to learn enough theory and programming tools to implement state-of-the-art models on standard image datasets. We'll also look at how to build your own image classification pipeline and then cover some of the recent developments in the field.

Outline

• Introduction to Supervised Machine Learning
• Preparing for Machine Learning
• Stochastic Gradient Descent
• Introduction to Artificial Neural Networks
• Convolutional Neural Networks
• MNIST
• Important Architectures and the state of the art
• Designing a CNN training pipeline

Prerequisite

Participants are encouraged to bring a laptop (preferably with a cuda-supported (nvidia) graphics card) preinstalled with Python 3.x, cuda (if the graphics card is present), Keras and TensorFlow if they wish to work through the hands-on examples presented in the workshop (familiarity with Python will help). It is also possible to simply attend the workshop without executing the hands-on examples.