Where Industry Meets Innovation

  • Contact Us
  • sign in Sign In
  • Sign in with certificate
mit campus

Resources

Search

  • View All
  • Industry Briefs
  • Research Reports
  • ILP Literature
  • Books and Other
  • Sort By:
  • Date
  • Title

Featured Publications

Loading
Please wait...

RECENT PUBLICATIONS

343 Results | Page 1 | 2 | 3 | .. | 67 | 68 | Last | Next
 

August 2016
ILP Research Group
Download Publication

RESEARCH SURVEYS - TOPICS LIST

ILP Research Group
This list is a guide to MIT ILP research surveys on topics that have been of interest to ILP member companies. The list includes research surveys from 2014 to present and is updated regularly.

August 2016
ILP Research Group
Request Research Survey

Autonomous Systems for Aerial Vehicles & Mobile Robots

ILP Research Survey
Survey of MIT research:

Aerospace robotics * dynamic locomotion * micro-air vehicle navigation & control * model-based embedded systems * robot locomotion * aerospace controls...




Please note that the ILP RESEARCH SURVEY LIST serves as a guide to MIT research on topics that have been of interest to ILP member companies and that the older the survey is, the more likely that it will contain some inactive projects.

August 2016
ILP Research Group
Request Research Survey

Autonomous Underwater Vehicles

ILP Research Report
Survey of MIT research:

Underwater robots * decision-making for autonomous wireless underwater power transfer * ship hull inspection * robust long-term visual mapping & localization * object recognition....




Please note that the ILP RESEARCH SURVEY LIST serves as a guide to MIT research on topics that have been of interest to ILP member companies and that the older the survey is, the more likely that it will contain some inactive projects.

September 2016
MIT Press
Order Book

Visual Cortex and Deep Networks

Tomaso A. Poggio and Fabio Anselmi
Learning Invariant Representations
The ventral visual stream is believed to underlie object recognition in primates. Over the past fifty years, researchers have developed a series of quantitative models that are increasingly faithful to the biological architecture. Recently, deep learning convolution networks—which do not reflect several important features of the ventral stream architecture and physiology—have been trained with extremely large datasets, resulting in model neurons that mimic object recognition but do not explain the nature of the computations carried out in the ventral stream. This book develops a mathematical framework that describes learning of invariant representations of the ventral stream and is particularly relevant to deep convolutional learning networks.

The authors propose a theory based on the hypothesis that the main computational goal of the ventral stream is to compute neural representations of images that are invariant to transformations commonly encountered in the visual environment and are learned from unsupervised experience. They describe a general theoretical framework of a computational theory of invariance (with details and proofs offered in appendixes) and then review the application of the theory to the feedforward path of the ventral stream in the primate visual cortex.


About the authors:

Tomaso A. Poggio is Eugene McDermott Professor in the Department of Brain and Cognitive Sciences at MIT, where he is also Director of the Center for Brains, Minds, and Machines and Codirector of the Center for Biological and Computational Learning. He is coeditor of Perceptual Learning (MIT Press).

Fabio Anselmi is a Postdoctoral Fellow in the Istituto Italiano di Tecnologia Laboratory for Computational and Statistical Learning at MIT and part of the Center for Brains, Minds, and Machines.

July 2016
ILP Research Group
Request Research Survey

Climate Change

ILP Research Survey
Survey of MIT research:

Atmospheric chemistry/science * agriculture/food/water * biogeochemistry * carbon capture * climate modeling/simulation * materials * oceans * policy/economics * climate/weather/precipitation/storms..




Please note that the ILP RESEARCH SURVEY LIST serves as a guide to MIT research on topics that have been of interest to ILP member companies and that the older the survey is, the more likely that it will contain some inactive projects.