A high-bias, low-variance introduction to Machine Learning for physicists

arXiv.org Machine Learning

Machine Learning (ML) is one of the most exciting and dynamic areas of modern research and application. The purpose of this review is to provide an introduction to the core concepts and tools of machine learning in a manner easily understood and intuitive to physicists. The review begins by covering fundamental concepts in ML and modern statistics such as the bias-variance tradeoff, overfitting, regularization, and generalization before moving on to more advanced topics in both supervised and unsupervised learning. Topics covered in the review include ensemble models, deep learning and neural networks, clustering and data visualization, energy-based models (including MaxEnt models and Restricted Boltzmann Machines), and variational methods. Throughout, we emphasize the many natural connections between ML and statistical physics. A notable aspect of the review is the use of Python notebooks to introduce modern ML/statistical packages to readers using physics-inspired datasets (the Ising Model and Monte-Carlo simulations of supersymmetric decays of proton-proton collisions). We conclude with an extended outlook discussing possible uses of machine learning for furthering our understanding of the physical world as well as open problems in ML where physicists maybe able to contribute. (Notebooks are available at https://physics.bu.edu/~pankajm/MLnotebooks.html )


Sketch Worksheets in STEM Classrooms: Two Deployments

AAAI Conferences

Sketching can be a valuable tool for science education, but it is currently underutilized. Sketch worksheets were developed to help change this, by using AI technology to give students immediate feedback and to give instructors assistance in grading. Sketch worksheets use visual representations automatically computed by CogSketch, which are combined with conceptual information from the OpenCyc ontology. Feedback is provided to students by comparing an instructor’s sketch to a student’s sketch, using the Structure-Mapping Engine. This paper describes our experiences in deploying sketch worksheets in two types of classes: Geoscience and AI. Sketch worksheets for introductory geoscience classes were developed by geoscientists at University of Wisconsin-Madison, authored using CogSketch and used in classes at both Wisconsin and Northwestern University. Sketch worksheets were also developed and deployed for a knowledge representation and reasoning course at Northwestern. Our experience indicates that sketch worksheets can provide helpful on-the-spot feedback to students, and significantly improve grading efficiency, to the point where sketching assignments can be more practical to use broadly in STEM education.


Educational Robotics in Brooklyn

AAAI Conferences

We describe a number of efforts to engage university students with robotics through teaching and outreach. Teaching runs the gamut from undergraduate introductory computer science to graduate-level artificial intelligence courses. Outreach involves collaborations between students and New York City public school classrooms. Our efforts have always involved team-based projects that culminate in demonstrations or competitions, usually based on challenges from RoboCupJunior. Several research projects have followed from these initiatives. Here, we relate some lessons learned and outline new research avenues that we are pursuing to overcome some of the issues.


One Hundred Challenge Problems for Logical Formalizations of Commonsense Psychology

AAAI Conferences

We present a new set of challenge problems for the logical formalization of commonsense knowledge, called Triangle-COPA. This set of one hundred problems is smaller than other recent commonsense reasoning question sets, but is unique in that it is specifically designed to support the development of logic-based commonsense theories, via two means. First, questions and potential answers are encoded in logical form using a fixed vocabulary of predicates, eliminating the need for sophisticated natural language processing pipelines. Second, the domain of the questions is tightly constrained so as to focus formalization efforts on one area of inference, namely the commonsense reasoning that people do about human psychology. We describe the authoring methodology used to create this problem set, and our analysis of the scope of requisite commonsense knowledge. We then show an example of how problems can be solved using an implementation of weighted abduction.


fastai/numerical-linear-algebra

#artificialintelligence

This course is focused on the question: How do we do matrix computations with acceptable speed and acceptable accuracy? This course was taught in the University of San Francisco's Masters of Science in Analytics program, summer 2017 (for graduate students studying to become data scientists). The course is taught in Python with Jupyter Notebooks, using libraries such as Scikit-Learn and Numpy for most lessons, as well as Numba (a library that compiles Python to C for faster performance) and PyTorch (an alternative to Numpy for the GPU) in a few lessons. Accompanying the notebooks is a playlist of lecture videos, available on YouTube. If you are ever confused by a lecture or it goes too quickly, check out the beginning of the next video, where I review concepts from the previous lecture, often explaining things from a new perspective or with different illustrations, and answer questions.