A distributed deep learning architecture for automatic speech recognition that shortens run time without compromising model accuracy.
IBM Research shares new results at SysML that push the envelope for deep learning inference, enabling high accuracy down to 2-bit precision.
A "biological" learning algorithm for neural networks that learns in an unsupervised fashion and performs well in image classification.
Quantum computers are extremely susceptible to “noise” from their environment – which leads to errors in the computation.
Magnetic materials could be at the forefront of an upcoming revolution in electronics.
New research shows that the number of mitochondria in a cell is associated with drug resistance, which could have a far-reaching impact in cancer treatment.
An interactive career goal recommender framework that uses dialogue to incorporate user feedback and interactively improve the recommendations.
The patterning of molecules is critical in applications including microarrays, tissue engineering, biosensors, biomaterials and fundamental cell studies.