Reconfigurable devices offer the ability to program electronic circuits on demand. In this
work, we demonstrated on-demand creation of artificial neurons, synapses, and memory …

The goal of continuous learning is to acquire and fine-tune knowledge incrementally without
erasing already existing knowledge. How to mitigate this erasure, known as catastrophic …

Introduction Bone scintigraphy, a nuclear medicine technique, is widely used for the
detection of bone metastasis. Deep learning has also been used in bone scan classification …

Stochastic gradient descent requires that training samples be drawn from a uniformly
random distribution of the data. For a deployed system that must learn online from an …

Limited progress has been made in continual unsupervised learning of representations,
especially in reusing, expanding, and continually disentangling learned semantic factors …

Realtime environments change even as agents perform action inference and learning, thus
requiring high interaction frequencies to effectively minimize regret. However, recent …

As the research community aims to build better AI assistants that are more dynamic and
personalized to the diversity of humans that they interact with, there is increased interest in …

An intelligent system capable of continual learning is one that can process and extract
knowledge from potentially infinitely long streams of pattern vectors. The major challenge …

Current deep learning architectures show remarkable performance when trained in large-
scale, controlled datasets. However, the predictive ability of these architectures significantly …

Using neural networks in the reinforcement learning (RL) framework has achieved notable
successes. Yet, neural networks tend to forget what they learned in the past, especially …