Tue,Thur 9:30-11:00 pm
It has been a long held goal to build machines capable of automatically improving based on their experience and size. In his 1968 paper, "'Memo' Functions and Machine Learning",(Nature, vol. 218, no. 5136, pp. Donald Michie conceretely challenged computer scientists with the following practical goal:
``It would be useful if computers could learn from experience and thus automatically improve the efficiency of their own programs during execution... When I write a clumsy program for a contemporary computer a thousand runs on the machine do not re-educate my handiwork. On every execution, each time-wasting blemish and crudity, each needless test and redundant evaluation, is meticulously reproduced.''Over the past several years we have been developing the concept of Programmable Smart Machines (PSMs): Hybrid computing systems that behave as programmed but transparently learn and automatically improve their operation. Both from the theoretical and practical point of view, our work attempts to side-step the traditional bottlenecks associated with the von Neumann architecture while preserving its programming model. In this course we will look at a cross section of the material that has informed and influenced our work including both applied and theortical topics. These topics will include material from complexity theory, computer architecture, operating systems, machine learning and biologically inspired computation. A fundmental aspect of this course is to identify and define open questions that the work raises.
The course will predominately be structured as a seminar in which each week we will be looking at one or two research papers. You will be required to submit weekly reviews and actively participate in the discussions.
Jonathan Appavoo, jappavoo@bu.edu
Steve Homer, and jappavoo@bu.edu
Amos Waterland, jappavoo@bu.edu
This course is targeted towards advanced undergraduate and graduate students. We encourage participation of both theory and systems students you are willing to push the boundaries of what you have been thinking about. You are encouraged to incoporate your personal interests and background into the class material.
Students taking this class must have some permision from the instructors, be a senior or graduate student and be proficient in:
Each week we will be covering on average two research papers you you will be expected to read, review and discuss. These papers will likely require that you find and read additional material as necessary to ensure your comprehension. Do not underestimate the amount of work this can be. You will be required to submit a written review of the papers prior to class. You will also be expected to actively participate in the in class discussion. Each student is expected to lead one more of the class discussions by summarizing the paper and seeding discussions with questions and observations based on the paper.
In addition, to the weekly papers, there will be a final project. For the project the students will explore an aspect of Programmable Smart Machines in detail. Projects can range from a theortical exploration to a applied experimental evaluation. The topic of your project must proposed and to the instructors and be approved. You will be expected to present a poster that discusses you project and submit a brief written report by the end of the term. As part of the proposal you will be expected to establish in conjunction with the instructors the goals and criteria for evalution. Each week you will provide a brief up date on the progess of your project.
The project is due by the end of the exam week. The project presentations will be given in the form of a final poster.
Students are expected to work individually on the weekly reviews. With instructor approval the final project maybe done in groups of two. There will be no final exam.
Grading scheme:
Reviews and Discussions: 40%
Project: 60%
Week 1 :
Week 2:
Week 3:
Week 4:
Week 5:
Week 6:
Week 7:
Week 8:
Week 9:
Week 10:
Week 11:
Weeks 12:
Week 13:
The project is due by the end of the exam week.
All course participants must adhere to the CAS Academic Conduct Code. All instances of adacemic dishonesty will be reported to the academic conduct committee.