Akida is intended for the creation, training, and testing of spiking neural networks (SNNs), and supports the development of systems for edge and enterprise products on the company’s Akida Neuromorphic System-on-Chip (NSoC).
The company said that applications that would benefit from the Akida solution include public safety, transportation, agricultural productivity, financial security, cybersecurity and healthcare.
These are large growth markets, for the company, and represent a $4.5bn opportunity by 2025.
The Development Environment includes the Akida Execution Engine, data-to-spike converters, and a model zoo of pre-created spiking neural network (SNN) models. The framework leverages the Python scripting language and its associated tools and libraries, including Jupyter notebooks, NumPy and Matplotlib.
“This development environment is the first phase in the commercialisation of neuromorphic computing based on BrainChip’s Akida neuron design,” said Bob Beachler, SVP of Marketing and Business Development. “It provides everything a user needs to develop, train, and run inference for spiking neural networks. Akida is targeted at high-growth markets that provide a multi-billion dollar opportunity and we are already engaged with leading companies in major market segments.”
The Akida Execution Engine is at the center of the framework and contains a software simulation of the Akida neuron, synapses, and the multiple supported training methodologies. Accessed through API calls in a Python script, users can specify their neural network topologies, training method, and datasets for execution. Based on the structure of the Akida neuron, the execution engine supports multiple training methods, including unsupervised training and unsupervised training with a labelled final layer.
The development environment natively accepts spiking data created by Dynamic Vision Sensors (DVS). However, there are many other types of data that can be used with SNNs. Embedded in the Akida Execution Engine are data-to-spike converters, which convert common data formats such as image information (pixels) into the spikes required for an SNN. The development environment will initially ship with a pixel-to-spike data converter, to be followed by converters for audio and big data requirements in cybersecurity, financial information and the Internet-of-Things data. Users are also able to create their own proprietary data to spike converters to be used within the development environment.
The Akida Development Environment also includes pre-created SNN models. Currently available models include a multi-layer perceptron implementation for MNIST in DVS format, a 7-layer network optimized for the CIFAR-10 dataset, and a 22-layer network optimised for the ImageNet dataset. These models can be the basis for users to modify, or to create their own custom SNN models.
