BWSI Course - Autonomous Cognitive Assistance (Cog*Works)

Artificial intelligence research has achieved a dramatic resurgence in recent years, as innovation of novel deep learning and other machine learning tools has enabled machine performance surpassing humans in specific cognitive tasks. New records in “machine thinking” seem to be set almost daily. This summer, the BWSI is offering students a chance to learn and use the state-of-the-art machine learning tools in a program called Cog*Works: Build your own Cognitive Assistant. The program will guide students in learning and applying the foundational technologies of artificial intelligence for building cognitive assistants. Students who have successfully completed the online course will be considered for participation in the summer program in which teams of students will leverage professional cognition services (e.g., Amazon Alexa/Echo) and open-source tools in conjunction with their own machine learning tools to develop cognitive systems. The program will be divided into modules during which students will implement and explore algorithms in core areas of natural language processing and machine cognition. These capabilities will be composed to create end-to-end cognitive assistants that will compete against each other at the end of the program.

 

This program consists of two components: (1) online course from January to May, open to all interested and committed students and (2) a four-week summer program for a  group of students, July 6– July 31. During the course, the students will be trained to understand the basics of Python, Git, natural language processing and machine learning through a series of online teaching modules. Students will build services that are both functional and fun. By participating in the online and/or onsite portion of the program, students will develop experience in an area of computer science that is poised to play a critical role in shaping future technologies and applications across many industries.

Online Course

The online component for the Cog*Works course will contain important introductory material that will provide students with the background required to successfully complete the four-week summer course. In addition to the introductory material, the online course will include more advanced machine learning–specific material that will enable students to begin exploring problems specific to cognitive assistants.

 

Introduction and Prerequisites

  • Introduction to Python
  • Git & Github management tools
  • Perspectives on machine learning

Autonomous Cognitive Assistants

  • Advanced NumPy
  • Simple image classification with Python
  • Introduction to neural networks
  • Introduction to Web Services
  • Introduction to Microsoft Cortana ©, and Amazon Alexa © services

Summer Course

The four-week summer component of the BWSI Cog*Works course aims to guide students through the process of creating their own cognitive assistants. Daily lectures from course instructors and guest speakers will solidify and expand upon the content from the online portion of the course. Students will collaborate in small groups to complete milestone projects that are based on their lecture materials. These projects will allow for creative customization and enhancements from the students, and weekly awards will be given to the group(s) with the most "interesting" projects. Ultimately, these projects will serve as the components that compose an end-to-end cognitive assistant.

The following is a rough outline for the summer course:

Week 1: Audio

  • Python/NumPy/Github review
  • Audio recording, sampling, and encoding
  • Discrete Fourier transforms and their applications
  • Pattern recognition in audio data
  • Audio capstone project

Week 2: Visual

  • Review of machine learning concepts
  • Coding your own autograd library
  • Training dense neural networks
  • CNNs and RNNs
  • Visual capstone project

Week 3: Language

  • Representing written language numerically
  • Document comparison and summarization
  • Training a language model
  • Training word embedding’s
  • Information retrieval
  • NLP capstone project

Week 4: Challenges

  • Customize your own neural network