Search Results for author:
Found 6 papers, 1 papers with code
Interactivity: the missing link between virtual reality technology and drug discovery pipelines
The potential of virtual reality (VR) to contribute to drug design and development has been recognised for many years.
Are there any 'object detectors' in the hidden layers of CNNs trained to identify objects or scenes?
We find that the different measures provide different estimates of object selectivity, with precision and CCMAS measures providing misleadingly high estimates.
Under what circumstances do local codes emerge in feed-forward neural networks
Pseudo-deep networks (2 hidden layers) which have many LCs lose them when common aspects of deep-NN research are applied (large training data, ReLU activations, early stopping on training accuracy and softmax), suggesting that LCs may not be found in deep-NNs.
Selectivity metrics can overestimate the selectivity of units: a case study on AlexNet
These findings highlight the problem with current selectivity measures and show that new measures are required in order to provide a better assessment of learned representations in NNs.
When and where do feed-forward neural networks learn localist representations?
We find that the number of local codes that emerge from a NN follows a well-defined distribution across the number of hidden layer neurons, with a peak determined by the size of input data, number of examples presented and the sparsity of input data.
Spiking memristor logic gates are a type of time-variant perceptron
Memristors are low-power memory-holding resistors thought to be useful for neuromophic computing, which can compute via spike-interactions mediated through the device's short-term memory.
