NeuroNavigator: A Hippocampus-Inspired Cognitive Architecture for Spiking Network Implementation
نویسندگان
چکیده
Despite recent impressive progress in automated planning and navigation tools, artifacts still lack robustness and flexibility of biological systems. In order to mimic biology, it is necessary to use principles of dynamics and architecture found in the brain. Here we translate our biologically inspired model of spatial learning and navigation (Samsonovich and Ascoli, L&M 2005) into a model suitable for implementation in spiking networks with STDP synapses, based on soon to become available hardware. Simulation studies of the model prove its robustness and scalability. The approach naturally extends to various types of action planning beyond the spatial domain. The architecture can be used in autonomous intelligent agents of various nature.
منابع مشابه
EMBRACE: Emulating Biologically–Inspired Architectures on Hardware
This paper highlights and discusses the current challenges in the implementation of large scale Spiking Neural Networks (SNNs) in hardware. A mixed-mode approach to realising scalable SNNs on a reconfigurable hardware platform is presented. The approach uses compact low power analogue spiking neuron cells, with a weight storage capability, interconnected using Network on Chip (NoC) routers. Res...
متن کاملA Model for Foraging Ants, Controlled by Spiking Neural Networks and Double Pheromones
A model of an Ant System where ants are controlled by a spiking neural circuit and a second order pheromone mechanism in a foraging task is presented. A neural circuit is trained for individual ants and subsequently the ants are exposed to a virtual environment where a swarm of ants performed a resource foraging task. The model comprises an associative and unsupervised learning strategy for the...
متن کاملVLSI Implementation of a Neuromorphic Spiking Pixel and Investigation of Various Focal-Plane Excitation Schemes
In this paper we describe a Neuromorphic spiking pixel architecture allowing the conversion of the light intensity into a pulse train signal. We first describe the spiking pixel architecture and its inherent advantages such as light adaptation mechanism and linear response characteristics. Inspired from biological visual systems and the integrate and fire oscillator, different inter-pixels inte...
متن کاملArtificial Grammar Processing in Spiking Neural Networks
In this paper we explore the feasibility of artificial (formal) grammar recognition (AGR) using spiking neural networks. A biologically inspired minicolumn architecture is designed as the basic computational unit. A network topography is defined based on the minicolumn architecture, here referred to as nodes, connected with excitatory and inhibitory connections. Nodes in the network represent u...
متن کاملLearning Spiking Neural Controllers for In-silico Navigation Experiments Learning Spiking Neural Controllers for In-silico Navigation Experiments
Artificial neural networks have been employed in many areas of cognitive systems research, ranging from low-level control tasks to high-level cognition. However, there is only few work on the use of spiking neural networks in these fields. Unlike artificial neurons, spiking neuron models are designed to approximate the dynamics of biological neurons. In this work, we developed a virtual environ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011