Dynamic Neural Fields
Dynamic Neural Fields (DNF) are neural attractor networks that generate stabilized activity patterns in recurrently connected populations of neurons. These activity patterns form the basis of neural representations, decision making, working memory, and learning. DNFs are the fundamental building block of [dynamic field theory](https://dynamicfieldtheory.org), a mathematical and conceptual framework for modeling cognitive processes in a closed behavioral loop.
Voltage of a selective dynamic neural field tracking moving input
What is lava-dnf?
lava-dnf is a library within the Lava software framework. The main building blocks in Lava are processes. lava-dnf provides processes and other software infrastructure to build architectures composed of DNFs. It also provides tools to direct sensory input to neural architectures and to read output, for instance for motor control.
The primary focus of lava-dnf today is on robotic applications: sensing and perception, motion control, behavioral organization, map formation, and autonomous (continual) learning. Neuromorphic hardware provides significant gains in both processing speed and energy efficiency compared to conventional implementations of DNFs on a CPU or GPU (e.g., using [cedar](https://cedar.ini.rub.de) or [cosivina](https://github.com/cosivina)).
Building DNF architectures
Based on spiking neurons
DNF dimensionality support for 0D, 1D, 2D, and 3D
Recurrent connectivity based on kernel functions
Forward connectivity to connect multiple DNFs
Structured input from spike generators
Examples demonstrating basic DNF regimes and instabilities
Detection of input
Selection of input
Working memory of input
Sensor and data input/output
from lava.lib.dnf.populations import Population from lava.lib.dnf.kernels import SelectiveKernel from lava.lib.dnf.connect import connect from lava.lib.dnf.operations import Instar, OneToOne # create population of 20x20 spiking neurons dnf = Population(shape=(20, 20)) # create a selective kernel kernel = SelectiveKernel(amp_exc=18, width_exc=[4, 4], global_inh=-15) # apply the kernel to the population to create a DNF with a selective regime connect(dnf, dnf, [Instar(kernel)])