Bioinspired Spike‐Based Hippocampus and Posterior Parietal Cortex Models for Robot Navigation and Environment Pseudomapping

Casanueva-Morato, Daniel; Ayuso-Martinez, Alvaro; Dominguez-Morales, Juan P.; Jimenez-Fernandez, Angel; Jimenez-Moreno, Gabriel; Perez-Peña, Fernando

doi:10.1002/aisy.202300132

Cited by 4 publications

(1 citation statement)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…T HE nervous system has demonstrated great computational capacity, adaptability and efficient resolution of complex problems [1]. Neuromorphic engineering focuses on the study, design and implementation of hardware and software systems that mimic the basic structural and functional principles of the biological nervous system in order to achieve such energy-efficient computational capabilities observed in nature [2]- [5].…”

Section: Introductionmentioning

confidence: 99%

A Bio-inspired Implementation of A Sparse-learning Spike-based Hippocampus Memory Model

Casanueva-Morato,

Ayuso-Martinez,

Dominguez-Morales

et al. 2024

IEEE Trans. Emerg. Topics Comput.

View full text Add to dashboard Cite

The brain is capable of solving complex problems simply and efficiently, far surpassing modern computers. In this regard, neuromorphic engineering focuses on mimicking the basic principles that govern the brain in order to develop systems that achieve such computational capabilities. Within this field, bio-inspired learning and memory systems are still a challenge to be solved, and this is where the hippocampus is involved. It is the region of the brain that acts as a short-term memory, allowing the learning and storage of information from all the sensory nuclei of the cerebral cortex and its subsequent recall. In this work, we propose a novel bio-inspired hippocampal memory model with the ability to learn memories, recall them from a fragment of itself (cue) and even forget memories when trying to learn others with the same cue. This model has been implemented on SpiNNaker using Spiking Neural Networks, and a set of experiments were performed to demonstrate its correct operation. This work presents the first simulation implemented on a special-purpose hardware platform for Spiking Neural Networks of a fully functional bio-inspired spike-based hippocampus memory model, paving the road for the development of future more complex neuromorphic systems.

show abstract

Section: Introductionmentioning

confidence: 99%

A Bio-inspired Implementation of A Sparse-learning Spike-based Hippocampus Memory Model

Casanueva-Morato,

Ayuso-Martinez,

Dominguez-Morales

et al. 2024

IEEE Trans. Emerg. Topics Comput.

View full text Add to dashboard Cite

show abstract

BrainQN: Enhancing the Robustness of Deep Reinforcement Learning with Spiking Neural Networks

Feng,

Cao,

et al. 2024

Advanced Intelligent Systems

View full text Add to dashboard Cite

As the third‐generation network succeeding artificial neural networks (ANNs), spiking neural networks (SNNs) offer high robustness and low energy consumption. Inspired by biological systems, the limitations of low robustness and high‐power consumption in deep reinforcement learning (DRL) are addressed by introducing SNNs. The Brain Q‐network (BrainQN) is proposed, which replaces the neurons in the classic Deep Q‐learning (DQN) algorithm with SNN neurons. BrainQN is trained using surrogate gradient learning (SGL) and ANN‐to‐SNN conversion methods. Robustness tests with input noise reveal BrainQN's superior performance, achieving an 82.14% increase in rewards under low noise and 71.74% under high noise compared to DQN. These findings highlight BrainQN's robustness and superior performance in noisy environments, supporting its application in complex scenarios. SGL‐trained BrainQN is more robust than ANN‐to‐SNN conversion under high noise. The differences in network output correlations between noisy and original inputs, along with training algorithm distinctions, explain this phenomenon. BrainQN successfully transitioned from a simulated Pong environment to a ball‐catching robot with dynamic vision sensors (DVS). On the neuromorphic chip PAICORE, it shows significant advantages in latency and power consumption compared to Jetson Xavier NX.

show abstract

Analog Implementation of a Spiking System for Performing Arithmetic Logic Operations on Mixed‐Signal Neuromorphic Processors

Ayuso‐Martinez,

Casanueva‐Morato,

Dominguez‐Morales

et al. 2024

Advanced Intelligent Systems

View full text Add to dashboard Cite

In recent years, physical limitations in the integration of transistors in computers have forced the search for low‐computational‐power alternatives in hardware design. Although doubts may arise regarding the limit of the relationship between performance and power consumption in computers, these disappear when considering the brain, which is one of the most efficient computing systems. In this way, bioinspired applications try to benefit from the low‐power consumption present in the biological nervous system. Previous work has shown the feasibility of implementing spiking neural networks that operate in a Boolean manner on digital platforms, such as SpiNNaker, using basic logic gates and a spiking memory, which suggests the potential for constructing a low‐power consumption spiking computer. This work takes a first step in the implementation of a spiking central processing unit by developing an arithmetic logic unit, which is an essential block for instruction execution, demonstrating its correct operation on Dynap‐SE1. The results confirm the feasibility of using this Boolean approach on this platform, despite certain limitations in the number of inputs and operating frequencies of the blocks, and pave the way for the construction of a spiking computer.

show abstract

Bioinspired Spike‐Based Hippocampus and Posterior Parietal Cortex Models for Robot Navigation and Environment Pseudomapping

Cited by 4 publications

References 53 publications

A Bio-inspired Implementation of A Sparse-learning Spike-based Hippocampus Memory Model

A Bio-inspired Implementation of A Sparse-learning Spike-based Hippocampus Memory Model

BrainQN: Enhancing the Robustness of Deep Reinforcement Learning with Spiking Neural Networks

Analog Implementation of a Spiking System for Performing Arithmetic Logic Operations on Mixed‐Signal Neuromorphic Processors

Contact Info

Product

Resources

About