A distributed deep learning architecture for automatic speech recognition that shortens run time without compromising model accuracy.
Quantum computers are extremely susceptible to “noise” from their environment – which leads to errors in the computation.
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.
Magnetic materials could be at the forefront of an upcoming revolution in electronics.