Topics in Applied Computation:
Advanced Practical Data Science
Office Hours: By appointment
Course helpline: firstname.lastname@example.org
Welcome to AC295: advanced practical data science. The course will be divided into three major topics:
1. How to scale a model from a prototype (often in jupyter notebooks) to the cloud. In this module, we cover virtual environments, containers, and virtual machines before learning about containers and Kubernetes. Along the way, students will be exposed to Dask.
2. How to use existing models for transfer learning. Transfer learning is a machine learning method where a model developed for a task is reused as the starting point for a model on a second task. It is a popular approach in deep learning where pre-trained models are used as the starting point on computer vision and natural language processing tasks. This could be very important, given the vast computing resources required to develop neural network models on these problems and the huge gains that these models can provide. In this part of the course, we will examine various pre-existing models and techniques in transfer learning.
3. In the third part, we will introduce several intuitive visualization tools for investigating and diagnosing models. We will be demonstrating a number of visualization tools ranging from the well established (like saliency maps) to recent examples that have appeared in https://distill.pub.
Lectures (online): Tuesday and Thursday 10:30-11:45am (and possibly depending on timezone of students repeat Tuesday and Thursday from 6:00-7:15pm)
Office Hours: (all times EST) (Office hours begin 09/08)
|William Palmer||Sunday||10:00-11:30 AM|
|Shivas Jayaram||Sunday||8:00 - 9:30 PM|
|Javid Lakha||Monday||4:30 - 6:00 PM|
|Faras Sadek||Monday||6:00 - 7:30 PM|
|Hai Bui||Wednesday||11:00 AM - 12:30 PM|
|Andrea Porelli||Thursday||1:00 -2:30 PM|
|Rashmi Banthia||Friday||8:30-10:00 AM|
|Yujiao Chen||Saturday||11:00 AM - 12:30 PM|