SaiSatish

SaiSatish

Giving bug-like bots a boost

Researchers have pioneered a new fabrication technique that enables them to produce low-voltage, power-dense, high endurance soft actuators for an aerial microrobot. These artificial muscles vastly improve the robot’s payload and allow it to achieve best-in-class hovering performance. Read More

Robots use fear to fight invasive fish

The invasive mosquitofish (Gambusia holbrooki) chews off the tails of freshwater fishes and tadpoles, leaving the native animals to perish while dining on other fishes’ and amphibians’ eggs. Researchers engineered a robot to scare mosquitofish away, revealing how fear alters…

Creating the human-robotic dream team

Using autonomous vehicle guidelines, a team has developed a system to improve interactions between people and robots. The way people interact safely with robots is at the forefront of today’s research related to automation and manufacturing, explains a researcher. She…

Interpretable Deep Learning for Time Series Forecasting

Posted by Sercan O. Arik, Research Scientist and Tomas Pfister, Engineering Manager, Google Cloud Multi-horizon forecasting, i.e. predicting variables-of-interest at multiple future time steps, is a crucial challenge in time series machine learning. Most real-world datasets have a time component,…

A Fast WordPiece Tokenization System

Posted by Xinying Song, Staff Software Engineer and Denny Zhou, Senior Staff Research Scientist, Google Research Tokenization is a fundamental pre-processing step for most natural language processing (NLP) applications. It involves splitting text into smaller units called tokens (e.g., words…

AI models microprocessor performance in real-time

Computer engineers have developed a new AI method for accurately predicting the power consumption of any type of computer processor more than a trillion times per second while barely using any computational power itself. Dubbed APOLLO, the technique has been…

More Efficient In-Context Learning with GLaM

Posted by Andrew M Dai and Nan Du, Research Scientists, Google Research, Brain Team Large language models (e.g., GPT-3) have many significant capabilities, such as performing few-shot learning across a wide array of tasks, including reading comprehension and question answering…