1 code implementation • 9 Aug 2019 • Leendert A Remmelzwaal, George F R Ellis, Jonathan Tapson, Amit K Mishra
In this paper we introduce a novel Salience Affected Artificial Neural Network (SANN) that models the way neuromodulators such as dopamine and noradrenaline affect neural dynamics in the human brain by being distributed diffusely through neocortical regions, allowing both salience signals to modulate cognition immediately, and one time learning to take place through strengthening entire patterns of activation at one go.
no code implementations • 18 Jul 2019 • Saeed Afshar, Ying Xu, Jonathan Tapson, André van Schaik, Gregory Cohen
A novel heuristic method for network size selection is proposed which makes use of noise events and their feature representations.
31 code implementations • 17 Feb 2017 • Gregory Cohen, Saeed Afshar, Jonathan Tapson, André van Schaik
The MNIST dataset has become a standard benchmark for learning, classification and computer vision systems.
Ranked #6 on Image Classification on EMNIST-Digits
no code implementations • 14 Mar 2016 • Saeed Afshar, Gregory Cohen, Tara Julia Hamilton, Jonathan Tapson, Andre van Schaik
This variance motivated the investigation of event-based decaying memory surfaces in comparison to time-based decaying memory surfaces to capture the temporal aspect of the event-based data.
no code implementations • 13 Mar 2016 • Runchun Wang, Chetan Singh Thakur, Tara Julia Hamilton, Jonathan Tapson, André van Schaik
The decay generator will then generate an exponential decay, which will be used by the STDP adaptor to perform the weight adaption.
no code implementations • 3 Sep 2015 • Ying Xu, Chetan Singh Thakur, Tara Julia Hamilton, Jonathan Tapson, Runchun Wang, Andre van Schaik
The architecture consists of an analogue chip and a control module.
no code implementations • 3 Sep 2015 • Runchun Wang, Chetan Singh Thakur, Tara Julia Hamilton, Jonathan Tapson, Andre van Schaik
We present an analogue Very Large Scale Integration (aVLSI) implementation that uses first-order lowpass filters to implement a conductance-based silicon neuron for high-speed neuromorphic systems.
1 code implementation • 21 Jul 2015 • Runchun Wang, Chetan Singh Thakur, Tara Julia Hamilton, Jonathan Tapson, Andre van Schaik
The architecture is not limited to handwriting recognition, but is generally applicable as an extremely fast pattern recognition processor for various kinds of patterns such as speech and images.
no code implementations • 10 Jul 2015 • Chetan Singh Thakur, Runchun Wang, Tara Julia Hamilton, Jonathan Tapson, Andre van Schaik
Additionally, we characterise each neuron and discuss the statistical variability of its tuning curve that arises due to random device mismatch, a desirable property for the learning capability of the TAB.
no code implementations • 11 May 2015 • Chetan Singh Thakur, Runchun Wang, Saeed Afshar, Gregory Cohen, Tara Julia Hamilton, Jonathan Tapson, Andre van Schaik
We propose a sign-based online learning (SOL) algorithm for a neuromorphic hardware framework called Trainable Analogue Block (TAB).
no code implementations • 2 Mar 2015 • Chetan Singh Thakur, Tara Julia Hamilton, Runchun Wang, Jonathan Tapson, André van Schaik
These neuronal populations are characterised by a diverse distribution of tuning curves, ensuring that the entire range of input stimuli is encoded.
no code implementations • 2 Mar 2015 • Chetan Singh Thakur, Tara Julia Hamilton, Jonathan Tapson, Richard F. Lyon, André van Schaik
Here, we implement the Cascade of Asymmetric Resonators (CAR) model of the cochlea on an FPGA.
no code implementations • 29 Dec 2014 • Mark D. McDonnell, Migel D. Tissera, Tony Vladusich, André van Schaik, Jonathan Tapson
Our close to state-of-the-art results for MNIST and NORB suggest that the ease of use and accuracy of the ELM algorithm for designing a single-hidden-layer neural network classifier should cause it to be given greater consideration either as a standalone method for simpler problems, or as the final classification stage in deep neural networks applied to more difficult problems.
no code implementations • 11 Nov 2014 • Saeed Afshar, Libin George, Jonathan Tapson, Andre van Schaik, Philip de Chazal, Tara Julia Hamilton
We have added a simplified neuromorphic model of Spike Time Dependent Plasticity (STDP) to the Synapto-dendritic Kernel Adapting Neuron (SKAN).
no code implementations • 6 Aug 2014 • Saeed Afshar, Libin George, Jonathan Tapson, Andre van Schaik, Tara Julia Hamilton
This paper describes the Synapto-dendritic Kernel Adapting Neuron (SKAN), a simple spiking neuron model that performs statistical inference and unsupervised learning of spatiotemporal spike patterns.
no code implementations • 12 Jun 2014 • Philip de Chazal, Jonathan Tapson, André van Schaik
We present an alternative to the pseudo-inverse method for determining the hidden to output weight values for Extreme Learning Machines performing classification tasks.
no code implementations • 11 Jun 2014 • Jonathan Tapson, Philip de Chazal, André van Schaik
In the absence of supervised training for the input weights, random linear combinations of training data samples are used to project the input data to a higher dimensional hidden layer.
no code implementations • 30 May 2014 • Jonathan Tapson, André van Schaik
The modifications involve the re-definition of hidden layer units as synaptic kernels, in which the input delta functions are transformed into continuous-valued signals using a variety of impulse-response functions.
no code implementations • 30 May 2014 • André van Schaik, Jonathan Tapson
The ELM method has become widely used for classification and regressions problems as a result of its accuracy, simplicity and ease of use.
no code implementations • 13 Jun 2013 • Saeed Afshar, Gregory Cohen, Runchun Wang, Andre van Schaik, Jonathan Tapson, Torsten Lehmann, Tara Julia Hamilton
In this paper we present the biologically inspired Ripple Pond Network (RPN), a simply connected spiking neural network that, operating together with recently proposed PolyChronous Networks (PCN), enables rapid, unsupervised, scale and rotation invariant object recognition using efficient spatio-temporal spike coding.