Search
Design is major stepping stone toward portable artificial-intelligence devices.
Random walks are at the heart of many existing network embedding methods.However, such algorithms have many limitations that arise from the use ofrandom walks, e.g., the features resulting from these methods are unable totransfer to new nodes and graphs as they are tied to vertex identity. In...
Math professor Philippe Rigollet, once a “not very disciplined” student, moves between computer science and statistics.
This spring, the MIT School of Science welcomes three new professors in the departments of Brain and Cognitive Sciences, and Earth, Atmospheric and Planetary Sciences.Michael Halassa aims to understand the neural basis of cognitive control and flexibility, particularly as it relates to attention…
Distributed Support Vector Machines (DSVM) have been developed to solve large-scale classification problems in networked systems with a large number of sensors and control units. However, the systems become more vulnerable as detection and defense are increasingly difficult and expensive. This work...
Machine-learning system finds patterns in materials “recipes,” even when training data is lacking.
Platform analyzes big data to answer plain-language business queries in minutes instead of months.
Model reduction is a central problem in analyzing complex systems andhigh-dimensional data. We study the state compression of finite-state Markovprocess from its empirical trajectories. We adopt a low-rank model which ismotivated by the state aggregation of controlled systems. A spectral method...
A new automated machine-learning system performs as well or better than its human counterparts — and works 100 times faster.
Results may help explain how humans do the same thing.
Technique illuminates the inner workings of artificial-intelligence systems that process language.
Improved recommendation algorithm should work especially well when ratings data are “sparse.”
Class taught by Vivienne Sze and Joel Emer brings together traditionally separate disciplines for advances in deep learning.
System could pore through millions of research papers to extract “recipes” for producing materials.
System for performing “tensor algebra” offers 100-fold speedups over previous software packages.
In this paper, two approaches are proposed to the definition of abnormallyextremal precipitation. These approaches are based on the negative binomialmodel for the distribution of duration of wet periods measured in days. Thismodel demonstrates excellent fit with real data and provides a theoretical...
Web-based system automatically evaluates proposals from far-flung data scientists.
MIT research scientist is exploring how machine learning can predict and prevent disruptions in reactors.
Multidimensional hypoelliptic diffusions arise naturally as models ofneuronal activity. Estimation in those models is complex because of thedegenerate structure of the diffusion coefficient. We build a consistentestimator of the drift and variance parameters with the help of a discretizedlog...
Using smartphone cameras, system for seeing around corners could help with self-driving cars and search-and-rescue.
Stay in the loop
Subscribe to our newsletter for a weekly update on the latest podcast, news, events, and jobs postings.