Most successful computer vision models transform low-level features, such as Gabor filter responses, into richer representations of intermediate or mid-level complexity for downstream visual tasks.
A novel heuristic method for network size selection is proposed which makes use of noise events and their feature representations.
Neuromorphic engineering (NE) encompasses a diverse range of approaches to information processing that are inspired by neurobiological systems, and this feature distinguishes neuromorphic systems from conventional computing systems.
These neuronal populations are characterised by a diverse distribution of tuning curves, ensuring that the entire range of input stimuli is encoded.
Here, we implement the Cascade of Asymmetric Resonators (CAR) model of the cochlea on an FPGA.
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.
We present an alternative to the pseudo-inverse method for determining the hidden to output weight values for Extreme Learning Machines performing classification tasks.
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.
The ELM method has become widely used for classification and regressions problems as a result of its accuracy, simplicity and ease of use.