Machine learning

MIT researchers have developed a neural-network model that can analyze raw text and audio data from interviews to discover speech patterns indicative of depression. This method could be used to develop diagnostic aids for clinicians that can detect signs of depression in natural conversation.

Model can more naturally detect depression in conversations

Neural network learns speech patterns that predict depression in clinical interviews.

August 29, 2018

MIT researchers have developed a machine-learning model that groups patients into subpopulations by health status to better predict a patient’s risk of dying during their stay in the ICU. This technique outperforms "global" mortality-prediction models and reveals performance disparities of those models across specific patient subpopulations.

Model improves prediction of mortality risk in ICU patients

By training on patients grouped by health status, neural network can better estimate if patients will die in the hospital.

August 29, 2018

Julia 1.0, developed and incubated at MIT, was officially released to the public during JuliaCon, an annual conference of Julia users held recently in London.

MIT-created programming language Julia 1.0 debuts

The dynamic programming language, which is free and open source, combines the speed and popular features of the best scientific and technical software.

August 27, 2018

A novel encryption method devised by MIT researchers secures data used in online neural networks, without dramatically slowing their runtimes, which holds promise for medical-image analysis using cloud-based neural networks and other applications.

More efficient security for cloud-based machine learning

Novel combination of two encryption techniques protects private data, while keeping neural networks running quickly.

August 17, 2018

MIT researchers aim to improve the quality of life for patients suffering from glioblastoma, the most aggressive form of brain cancer, with a machine-learning model that makes chemotherapy and radiotherapy dosing regimens less toxic but still as effective as human-designed regimens.

Artificial intelligence model “learns” from patient data to make cancer treatment less toxic

Machine-learning system determines the fewest, smallest doses that could still shrink brain tumors.

August 9, 2018

MIT professor Silvio Micali, one of the leaders of the new FinTech@CSAIL initiative, speaks to industry leaders at the Stata Center.

CSAIL launches new initiative for financial technology

FinTech@CSAIL industry collaboration will work to improve business models, access to data, and security in the finance sector.

July 26, 2018

MIT Media Lab researchers have developed a machine-learning model that takes computers a step closer to interpreting our emotions as naturally as humans do. The model better captures subtle facial expression variations to better gauge moods. By using extra training data, the model can also be adapted to an entirely new group of people, with the same efficacy.

Helping computers perceive human emotions

Personalized machine-learning models capture subtle variations in facial expressions to better gauge how we feel.

July 24, 2018

Chemical engineering graduate student Connor Coley is researching ways to improve automation and computer assistance in synthesis planning and reaction optimization with medicinal chemistry applications.

Connor Coley named 2018 DARPA Riser

Chemical engineering graduate student is invited to participate in the agency's 60th anniversary symposium in September.

July 16, 2018

An atmospheric scene, called "Forest," with video from thesilentwatcher.com, is part of the Mediated Atmospheres project by Nan Zhao.

Smart office enables a personalized workplace atmosphere

Project out of the MIT Media Lab uses biosensors and machine learning to optimize the sensory experience in individual work environments.

July 13, 2018

The image is an artist’s visualization of a nucleus as studied in numerical simulations, created using DeepArt neural network visualization software.

Project to elucidate the structure of atomic nuclei at the femtoscale

Laboratory for Nuclear Science project selected to explore machine learning for lattice quantum chromodynamics.

July 6, 2018

MIT researchers have developed a machine-learning model that better selects molecule candidates for therapeutics, while also allowing for automated modification of the molecular structure for higher potency. The innovation has potential to speed up drug development.

Automating molecule design to speed up drug development

Machine-learning model could help chemists make molecules with higher potencies, much more quickly.

July 6, 2018

A new AI system can look at an image and determine which set of pixels are responsible for making specific sets of soundwaves.

An AI system for editing music in videos

Given a video of a musical performance, CSAIL’s deep-learning system can make individual instruments louder or softer.

July 5, 2018

MIT postdoc Cristina Rea records data about disruptions in fusion plasmas from the DIII-D control room.

Taming fusion with machine learning

Postdoc Cristina Rea's detour into banking provides a new route back to plasma research.

July 2, 2018

An example of a therapy session augmented with humanoid robot NAO [SoftBank Robotics], which was used in the EngageMe study. Tracking of limbs/faces was performed using the CMU Perceptual Lab's OpenPose utility.

Personalized “deep learning” equips robots for autism therapy

Machine learning network offers personalized estimates of children’s behavior.

June 27, 2018

MIT researchers describe a machine-learning algorithm that can register brain scans and other 3-D images more than 1,000 times more quickly using novel learning techniques.

Faster analysis of medical images

Algorithm makes the process of comparing 3-D scans up to 1,000 times faster.

June 18, 2018

MIT News | Massachusetts Institute of Technology

Browse By

Topics

Departments

Centers, Labs, & Programs

Schools

Topic