Backpropagation (BP), the standard learning algorithm for artificial neu...
Transformers are state-of-the-art networks for most sequence processing
...
Backpropagation (BP) is the most successful and widely used algorithm in...
Although deep Reinforcement Learning (RL) has proven successful in a wid...
Adaptive "life-long" learning at the edge and during online task perform...
The brain is the perfect place to look for inspiration to develop more
e...
Predictive coding (PC) is a general theory of cortical function. The loc...
To achieve the low latency, high throughput, and energy efficiency benef...
While commercial mid-air gesture recognition systems have existed for at...
Many real-world mission-critical applications require continual online
l...
Despite the recent success of deep reinforcement learning (RL), domain
a...
We present the Surrogate-gradient Online Error-triggered Learning (SOEL)...
Multiplicative stochasticity such as Dropout improves the robustness and...
Recent work suggests that synaptic plasticity dynamics in biological mod...
Spike-based communication between biological neurons is sparse and
unrel...
Spike-based communication between biological neurons is sparse and
unrel...
A growing body of work underlines striking similarities between spiking
...
Neural networks are commonly trained to make predictions through learnin...
Embedded, continual learning for autonomous and adaptive behavior is a k...
An ongoing challenge in neuromorphic computing is to devise general and
...
Current large scale implementations of deep learning and data mining req...
Spike-timing-dependent plasticity (STDP) incurs both causal and acausal
...
In recent years the field of neuromorphic low-power systems that consume...
We present an approach to constructing a neuromorphic device that respon...
The goal of a generative model is to capture the distribution underlying...
Restricted Boltzmann Machines (RBMs) and Deep Belief Networks have been
...