Machine learning

MIT researchers have developed a new approach to training speech-recognition systems that doesn’t depend on transcription. Instead, their system analyzes correspondences between images and spoken descriptions of those images, as captured in a large collection of audio recordings.

Learning words from pictures

System correlates recorded speech with images, could lead to fully automated speech recognition.

December 6, 2016

The researchers’ neural network was fed video from 26 terabytes of video data downloaded from the photo-sharing site Flickr. Researchers found the network can interpret natural sounds in terms of image categories. For instance, the network might determine that the sound of birdsong tends to be associated with forest scenes and pictures of trees, birds, birdhouses, and bird feeders.

Computer learns to recognize sounds by watching video

Machine-learning system doesn’t require costly hand-annotated data.

December 2, 2016

Tomaso Poggio, a professor of brain and cognitive sciences at MIT and director of the Center for Brains, Minds, and Machines, has long thought that the brain must produce “invariant” representations of faces and other objects, meaning representations that are indifferent to objects’ orientation in space, their distance from the viewer, or their location in the visual field.

How the brain recognizes faces

Machine-learning system spontaneously reproduces aspects of human neurology.

December 1, 2016

Given a still image from a scene, new deep-learning algorithm can create a brief video that simulates the future of that scene.

Creating videos of the future

Given a still image, CSAIL deep-learning system generates videos that predict what will happen next in a scene.

November 29, 2016

Tamara Broderick, assistant professor of electrical engineering and computer science at MIT, was a presenter at the 2016 Machine Intelligence Summit.

Meeting of the minds for machine intelligence

Industry leaders, computer scientists, and venture capitalists gather to discuss how smarter computers are remaking our world.

November 22, 2016

Information extraction — or automatically classifying data items stored as plain text — is a major topic of artificial-intelligence research.

Artificial-intelligence system surfs web to improve its performance

“Information extraction” system helps turn plain text into data for statistical analysis.

November 10, 2016

Researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have devised a way to train neural networks so that they provide not only predictions and classifications but rationales for their decisions.

Making computers explain themselves

New training technique would reveal the basis for machine-learning systems’ decisions.

October 27, 2016

A team, including researchers from MIT’s Computer Science and Artificial Intelligence Laboratory, has created a new set of algorithms that can efficiently fit probability distributions to high-dimensional data.

Finding patterns in corrupted data

New model-fitting technique is efficient even for data sets with hundreds of variables.

October 26, 2016

Researchers used sample images, like the ones on the top row, to identify several visual features that are highly correlated with judgments that a particular area is safe or unsafe. The left side shows a low level of safety while the right shows a high level. Highlighted areas on the middle row show “unsafe” areas while the bottom row shows “safe” areas in the image.

Quantifying urban revitalization

Combining cellphone data with perceptions of public spaces could help guide urban planning.

October 24, 2016

“The goal of all this is to present the interesting stuff to the data scientists so that they can more quickly address all these new data sets that are coming in,” says Max Kanter MEng ’15.

Automating big-data analysis

With new algorithms, data scientists could accomplish in days what has traditionally taken months.

October 21, 2016

Ankur Moitra named a 2016 Packard Fellow

October 17, 2016

MIT Media Lab Director Joi Ito (left), WIRED Editor-in-Chief Scott Dadich (center), and U.S. President Barack Obama confer in the Roosevelt Room of the White House.

President Obama discusses artificial intelligence with Media Lab Director Joi Ito

One-on-one conversation in WIRED focuses on advancements in artificial intelligence and how society should respond to related concerns.

October 14, 2016

The Laboratory for Social Machines, part of the MIT Media Lab, has launched a project called the Electome that charts Twitter in unique detail.

Q&A: How Twitter explains the 2016 election

“Electome” project charts the national conversation in unique detail.

September 26, 2016

A new computer system can automatically screen young children for speech and language disorders and, potentially, even provide specific diagnoses.

Automated screening for childhood communication disorders

Computer system could help identify subtle speech, language disorders in time for early intervention.

September 22, 2016

Imaging scientist and social impact inventor Ramesh Raskar of MIT is the 2016 recipient of the $500,000 Lemelson-MIT Prize.

Ramesh Raskar awarded $500,000 Lemelson-MIT Prize

Imaging scientist and inventor sets sights on launching peer-to-peer invention platforms for global impact.

September 13, 2016

MIT News | Massachusetts Institute of Technology

Browse By

Topics

Departments

Centers, Labs, & Programs

Schools

Topic