Abstract: A mechanism to control the stability and performance of weight-sharing methods for designing neural networks is provided. Network weights and architecture parameters of a super-net, including multiple sub-networks, are adjusted to reduce a loss determined, at least in part, from a sum, over layers of the sub-network, of measures of smoothness based on network weights in the layers. A sub-network of the super-net is selected dependent upon the adjusted architectural parameters.

Abstract: Disclosed is a novel neural network architecture and methods for generating neural network-based models from such architecture. A first version of the neural network, that is used for training purposes, includes one or more blocks in a first format that can then be replaced with corresponding blocks in a second format for execution. An executable model can thus be provided comprising a second version of the neural network including the one or more blocks in the second format. This then allows the training to be performed in a first, e.g. expanded format, but with a second, e.g. reduced, format model then provided for execution.

Abstract: Broadly speaking, the present techniques exploit the properties of correlated electron materials for artificial neural networks and neuromorphic computing. In particular, the present techniques provide apparatuses/devices that comprise at least one correlated electron switch (CES) element and which may be used as, or to form, an artificial neuron or an artificial synapse.

Abstract: The present disclosure advantageously provides a heterogenous system, and a method for generating an artificial neural network (ANN) for a heterogenous system. The heterogenous system includes a plurality of processing units coupled to a memory configured to store an input volume. The plurality of processing units includes first and second processing units. The first processing unit includes a first processor and is configured to execute a first ANN, and the second processing unit includes a second processor and is configured to execute a second ANN. The first and second ANNs respectively include an input layer, at least one processor-optimized hidden layer and an output layer. The second ANN hidden layers are different than the first ANN hidden layers.

Abstract: The present disclosure advantageously provides a heterogenous system, and a method for generating an artificial neural network (ANN) for a heterogenous system. The heterogenous system includes a plurality of processing units coupled to a memory configured to store an input volume. The plurality of processing units includes first and second processing units. The first processing unit includes a first processor and is configured to execute a first ANN, and the second processing unit includes a second processor and is configured to execute a second ANN. The first and second ANNs respectively include an input layer, at least one processor-optimized hidden layer and an output layer. The second ANN hidden layers are different than the first ANN hidden layers.

Abstract: Broadly speaking, embodiments of the present technique provide a neuron for a spiking neural network, where the neuron is formed of at least one Correlated Electron Random Access Memory (CeRAM) element or Correlated Electron Switch (CES) element.

Abstract: Broadly speaking, the present techniques exploit the properties of correlated electron materials for artificial neural networks and neuromorphic computing. In particular, the present techniques provide apparatuses/devices that comprise at least one correlated electron switch (CES) element and which may be used as, or to form, an artificial neuron or an artificial synapse.

Abstract: Broadly speaking, embodiments of the present technique provide a neuron for a spiking neural network, where the neuron is formed of at least one Correlated Electron Random Access Memory (CeRAM) element or Correlated Electron Switch (CES) element.