Search Results for author:
Found 4 papers, 0 papers with code
Task structure and nonlinearity jointly determine learned representational geometry
By studying the learning dynamics of networks with one hidden layer, we discovered that the network's activation function has an unexpectedly strong impact on the representational geometry: Tanh networks tend to learn representations that reflect the structure of the target outputs, while ReLU networks retain more information about the structure of the raw inputs.
The computational role of structure in neural activity and connectivity
One major challenge of neuroscience is finding interesting structures in a seemingly disorganized neural activity.
Memory capacity of neural network models
The memory capacity depends on the complexity of the synapses, the sparseness of the representations, the spatial and temporal correlations between memories and the specific way memories are retrieved.
Energy-efficient neuromorphic classifiers
We also show that the energy consumption of the IBM chip is typically 2 or more orders of magnitude lower than that of conventional digital machines when implementing classifiers with comparable performance.
