no code implementations • 20 Dec 2021 • Bojian Yin, Federico Corradi, Sander M. Bohte
When combined with a novel dynamic spiking neuron model, the Liquid-Time-Constant neuron, we show that SNNs trained with FPTT outperform online BPTT approximations, and approach or exceed offline BPTT accuracy on temporal classification tasks.
no code implementations • 12 Mar 2021 • Bojian Yin, Federico Corradi, Sander M. Bohte
Inspired by more detailed modeling of biological neurons, Spiking neural networks (SNNs) have been investigated both as more biologically plausible and potentially more powerful models of neural computation, and also with the aim of extracting biological neurons' energy efficiency; the performance of such networks however has remained lacking compared to classical artificial neural networks (ANNs).
Ranked #4 on Audio Classification on SSC
no code implementations • 25 Sep 2019 • Isabella Pozzi, Sander M. Bohte, Pieter R. Roelfsema
While much recent work has focused on biologically plausible variants of error-backpropagation, learning in the brain seems to mostly adhere to a reinforcement learning paradigm; biologically plausible neural reinforcement learning frameworks, however, were limited to shallow networks learning from compact and abstract sensory representations.
no code implementations • 16 Sep 2019 • Oliver Struckmeier, Kshitij Tiwari, Shirin Dora, Martin J. Pearson, Sander M. Bohte, Cyriel MA Pennartz, Ville Kyrki
Extracting and binding salient information from different sensory modalities to determine common features in the environment is a significant challenge in robotics.
no code implementations • 18 Feb 2019 • Bojian Yin, Siebren Schaafsma, Henk Corporaal, H. Steven Scholte, Sander M. Bohte
While modern convolutional neural networks achieve outstanding accuracy on many image classification tasks, they are, compared to humans, much more sensitive to image degradation.
no code implementations • 14 Feb 2019 • Anastasia Borovykh, Cornelis W. Oosterlee, Sander M. Bohte
In this paper we study the generalization capabilities of fully-connected neural networks trained in the context of time series forecasting.
no code implementations • 25 Jan 2019 • Shuaiqiang Liu, Cornelis W. Oosterlee, Sander M. Bohte
This paper proposes a data-driven approach, by means of an Artificial Neural Network (ANN), to value financial options and to calculate implied volatilities with the aim of accelerating the corresponding numerical methods.
no code implementations • 7 Sep 2016 • Davide Zambrano, Sander M. Bohte
It is an open question how real spiking neurons produce the kind of powerful neural computation that is possible with deep artificial neural networks, using only so very few spikes to communicate.
no code implementations • NeurIPS 2012 • Sander M. Bohte
Neural adaptation underlies the ability of neurons to maximize encoded information over a wide dynamic range of input stimuli.
no code implementations • NeurIPS 2012 • Jaldert Rombouts, Pieter Roelfsema, Sander M. Bohte
Neurons in association cortex play an important role in this process: during learning these neurons become tuned to relevant features and represent the information that is required later as a persistent elevation of their activity.
no code implementations • NeurIPS 2010 • Jaldert Rombouts, Sander M. Bohte
Here, we show that the actual neural spike-train itself can be considered as the fractional derivative, provided that the neural signal is approximated by a sum of power-law kernels.