相关论文: Storage Capacity Diverges with Synaptic Efficiency…

The unmatched ability of Deep Neural Networks in capturing complex patterns in large and noisy datasets is often associated with their large hypothesis space, and consequently to the vast amount of parameters that characterize model…

Theoretical models of neuronal function consider different mechanisms through which networks learn, classify and discern inputs. A central focus of these models is to understand how associations are established amongst neurons, in order to…

Protein synthesis-dependent, late long-term potentiation (LTP) and depression (LTD) at glutamatergic hippocampal synapses are well characterized examples of long-term synaptic plasticity. Persistent increased activity of the enzyme protein…

Synaptic delay parameterization of neural network models have remained largely unexplored but recent literature has been showing promising results, suggesting the delay parameterized models are simpler, smaller, sparser, and thus more…

In stochastic combinatorial optimization, algorithms differ in their adaptivity: whether or not they query realized randomness and adapt to it. Dean et al. (FOCS '04) formalize the adaptivity gap, which compares the performance of fully…

A fundamental feature of learning in animals is the "ability to forget" that allows an organism to perceive, model and make decisions from disparate streams of information and adapt to changing environments. Against this backdrop, we…

Unlike the brain, artificial neural networks, including state-of-the-art deep neural networks for computer vision, are subject to "catastrophic forgetting": they rapidly forget the previous task when trained on a new one. Neuroscience…

Energy efficient implementations and deployments of Spiking neural networks (SNNs) have been of great interest due to the possibility of developing artificial systems that can achieve the computational powers and energy efficiency of the…

Artificial Neural Networks (ANNs) suffer from catastrophic forgetting, where the learning of new tasks causes the catastrophic forgetting of old tasks. Existing Machine Learning (ML) algorithms, including those using Stochastic Gradient…

Stochastic control problems with delay are challenging due to the path-dependent feature of the system and thus its intrinsic high dimensions. In this paper, we propose and systematically study deep neural networks-based algorithms to solve…

Memories are stored, at least partly, as patterns of strong synapses. Given molecular turnover, how can synapses maintain strong for the years that memories can persist? Some models postulate that biochemical bistability maintains strong…

We consider a neural network with adapting synapses whose dynamics can be analitically computed. The model is made of $N$ neurons and each of them is connected to $K$ input neurons chosen at random in the network. The synapses are…

In many machine learning problems, large-scale datasets have become the de-facto standard to train state-of-the-art deep networks at the price of heavy computation load. In this paper, we focus on condensing large training sets into…

Deep learning's success has been attributed to the training of large, overparameterized models on massive amounts of data. As this trend continues, model training has become prohibitively costly, requiring access to powerful computing…

The recent discovered spatial-temporal information processing capability of bio-inspired Spiking neural networks (SNN) has enabled some interesting models and applications. However designing large-scale and high-performance model is yet a…

Spiking neurons can perform spatiotemporal feature detection by nonlinear synaptic and dendritic integration of presynaptic spike patterns. Multicompartment models of non-linear dendrites and related neuromorphic circuit designs enable…

Activity and parameter sparsity are two standard methods of making neural networks computationally more efficient. Event-based architectures such as spiking neural networks (SNNs) naturally exhibit activity sparsity, and many methods exist…

The inclusion of a macroscopic adaptive threshold is studied for the retrieval dynamics of both layered feedforward and fully connected neural network models with synaptic noise. These two types of architectures require a different method…

Deep Neural Networks (DNNs) suffer from a rapid decrease in performance when trained on a sequence of tasks where only data of the most recent task is available. This phenomenon, known as catastrophic forgetting, prevents DNNs from…

Debiasing language models from unwanted behaviors in Natural Language Understanding tasks is a topic with rapidly increasing interest in the NLP community. Spurious statistical correlations in the data allow models to perform shortcuts and…