Algorithms

Professor Ted Adelson's team created a soft robotic finger that uses embedded cameras and deep learning to enable high-resolution tactile sensing and “proprioception” (awareness of positions and movements of the body).

Giving soft robots feeling

In a pair of papers from MIT CSAIL, two teams enable better sense and perception for soft robotic grippers.

June 1, 2020

A new algorithm, called the Fast Loaded Dice Roller (FLDR), simulates the roll of dice to produce random integers. The dice, in this case, could have any number of sides, and they are “loaded,” or weighted, to make some sides more likely to come up than others.

Algorithm quickly simulates a roll of loaded dice

Approach for generating numbers at random may help analyses of complex systems, from Earth’s climate to financial markets.

May 28, 2020

Students participating in MIT Quest for Intelligence-funded UROP projects include: (clockwise from top left) Alon Kosowsky-Sachs, Isaac Wolverton, Kuan Wei Huang, and Karen Gu.

Undergraduates develop next-generation intelligence tools

UROP students explore applications in robotics, health care, language understanding, and nuclear engineering.

May 26, 2020

Search-and-rescue algorithm identifies hidden “traps” in ocean waters

Method may help quickly identify regions where objects — and missing people — may have converged.

May 26, 2020

Activation maps of neural network model for digital staining of tumors

Deep learning accurately stains digital biopsy slides

Pathologists who examined the computationally stained images could not tell them apart from traditionally stained slides.

May 22, 2020

Scanning electron micrograph of HIV-1 (in green) budding from a cultured lymphocyte

HIV genome bends over backwards to help virus take over cells

Differently shaped RNA molecules allow HIV to express different genes from the same RNA sequence.

May 11, 2020

MIT researchers have developed a kind of creativity test for generative models to see how far they can go in visualizing objects in photos from various angles and in different colors. The tool shows how much the model's imagination depends on the variety of images it has seen.

Visualizing the world beyond the frame

Researchers test how far artificial intelligence models can go in dreaming up varied poses and colors of objects and animals in photos.

May 6, 2020

MIT researchers have proposed a technique for shrinking deep learning models that they say is simpler and produces more accurate results than state-of-the-art methods. It works by retraining the smaller, pruned model at its faster, initial learning rate.

A foolproof way to shrink deep learning models

Researchers unveil a pruning algorithm to make artificial intelligence applications run faster.

April 30, 2020

MIT researchers used machine learning to find entirely new algorithms for encoding exploration. Their machine-designed algorithms outperformed human-designed algorithms on the wide range of simulated tasks and environments shown here.

Automating the search for entirely new “curiosity” algorithms

Researchers show that computers can “write” algorithms that adapt to radically different environments better than algorithms designed by humans.

April 28, 2020

Lead author Joseph DelPreto controls a "Conduct-A-Bot" drone with his arm muscles.

Muscle signals can pilot a robot

CSAIL's Conduct-A-Bot system uses muscle signals to cue a drone’s movement, enabling more natural human-robot communication.

April 27, 2020

MIT researchers have developed a new automated AI system with improved computational efficiency and a much smaller carbon footprint. The researchers’ system trains one large neural network comprising many pretrained subnetworks of different sizes that can be tailored to diverse hardware platforms without retraining.

Reducing the carbon footprint of artificial intelligence

MIT system cuts the energy required for training and running neural networks.

April 23, 2020

In this lidar map, AI algorithms have identified roads (red). By pairing this map with OpenStreetMaps, users can plan routes around roads that are deemed impassable and can do so at the scale of an entire sortie, which here covers about 400 square miles.

With lidar and artificial intelligence, road status clears up after a disaster

Automated tools can help emergency managers make decisions, plan routes, and quantify road damage at city scales.

April 21, 2020

This research started as part of a project started in class 2.168 (Learning Machines), which was instructed by Professor George Barbastathis (pictured).

Model quantifies the impact of quarantine measures on Covid-19’s spread

A machine learning algorithm combines data on the disease's spread with a neural network, to help predict when infections will slow down in each country.

April 16, 2020

To reduce lag times and increase quality in video streaming, mobile gaming, and other web services, researchers at MIT’s Computer Science and Artificial Intelligence Laboratory have designed a congestion-control scheme for time-varying wireless links, such as cellular networks.

Reducing delays in wireless networks

Congestion control system could help streaming video, mobile games, and other applications run more smoothly.

April 9, 2020

A simulation system invented at MIT to train driverless cars creates a photorealistic world with infinite steering possibilities, helping the cars learn to navigate a host of worse-case scenarios before cruising down real streets.

System trains driverless cars in simulation before they hit the road

Using a photorealistic simulation engine, vehicles learn to drive in the real world and recover from near-crash scenarios.

March 23, 2020

MIT News | Massachusetts Institute of Technology

Browse By

Topics

Departments

Centers, Labs, & Programs

Schools

Topic