26-09-2016, 10:25 AM
1456157247-EMBEDDEDSPIKINGNEURALNETWORKS.pptx (Size: 2.01 MB / Downloads: 6)
INTRODUCTION
NEURAL NETWORK is used refer a circuit of neurons that perform information processing using an approach to the problem different from the usual algorithmic computation of modern computer systems
ARTIFICIAL NEURAL NETWORKS are circuits which are made by the interconnection of artificial neurons which mimic the behaviour of biological neurons
Spiking neural networks
Spiking neural networks (SNNs) fall into the third generation of neural network models, increasing the level of realism in a neural simulation.
Spiking neural networks are better suited for hardware implementations due to two facts: inter-neuron communication consists of single bits and the neurons themselves are actually only weighed leaky integrators.
More specifically it will concentrate on embedded devices because they have the advantage that a processor is closely linked to the neural model, which can coordinate learning, reconfiguration, etc.
An artificial neuron is a mathematical function conceived as a model of biological neurons.
The artificial neuron receives one or more inputs (representing dendrites) and sums them to produce an output (representing a neuron's axon).
Artificial neural networks are generally presented as systems of interconnected "neurons" which can compute values from inputs.
the sum is passed through a non-linear function known as an activation function or transfer function.
The transfer functions usually have a sigmoid shape
Spiking neural network model usually uses ‘Integrate an fire model’ where the neurons are nothing but a leaky integrator, which fire an reset a neuron when a threshold is reached.