RECORD
Spatial computing in structured spiking neural networks with a robotic embodiment
Neurons and Cognition · Submitted 14 Dec 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim We show that the model enables training a neuro-robot according to Pavlovian conditioning.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
One of the challenges of modern neuroscience is creating a "living computer" based on neural networks grown in vitro. Such an artificial device is supposed to perform neurocomputational tasks and interact with the environment when embodied in a robot. Recent studies have identified the most critical challenge, the search for a neural network architecture to implement associative learning. This work proposes a model of modular architecture with spiking neural networks connected by unidirectional couplings. We show that the model enables training a neuro-robot according to Pavlovian conditioning. The robot's performance in obstacle avoidance depends on the ratio of the weights in inter-network couplings. We show that besides STDP, critical factors for successful learning are synaptic and neuronal competitions. We use the recently discovered shortest path rule to implement the synaptic competition. This method is ready for experimental testing. Strong inhibitory couplings implement the neuronal competition in the subnetwork responsible for the unconditional response. Empirical testing of this approach requires a technique for growing neural networks with a given ratio of excitatory and inhibitory neurons not available yet. An alternative is building a hybrid system with in vitro neural networks coupled through hardware memristive connections.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | One of the challenges of modern neuroscience is creating a "living computer" based on neural networks grown in vitro. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | Such an artificial device is supposed to perform neurocomputational tasks and interact with the environment when embodied in a robot. | background 1.00 | 0.05 | 0.03 | asserted 0.62 |
| s2 | Recent studies have identified the most critical challenge, the search for a neural network architecture to implement associative learning. | background 0.57 | 0.06 | 0.03 | asserted 1.00 |
| s3 | This work proposes a model of modular architecture with spiking neural networks connected by unidirectional couplings. | contribution 0.53 | 0.80 | 0.10 | asserted 0.95 |
| s4 | We show that the model enables training a neuro-robot according to Pavlovian conditioning. | result 0.86 | 0.89 | 0.48 | asserted 1.00 |
| s5 | The robot's performance in obstacle avoidance depends on the ratio of the weights in inter-network couplings. | result 1.00 | 0.82 | 0.12 | asserted 1.00 |
| s6 | We show that besides STDP, critical factors for successful learning are synaptic and neuronal competitions. | result 0.96 | 0.85 | 0.24 | asserted 1.00 |
| s7 | We use the recently discovered shortest path rule to implement the synaptic competition. | method 0.97 | 0.70 | 0.05 | asserted 1.00 |
| s8 | This method is ready for experimental testing. | future work 0.51 | 0.24 | 0.09 | asserted 0.98 |
| s9 | Strong inhibitory couplings implement the neuronal competition in the subnetwork responsible for the unconditional response. | method 0.89 | 0.52 | 0.09 | asserted 1.00 |
| s10 | Empirical testing of this approach requires a technique for growing neural networks with a given ratio of excitatory and inhibitory neurons not available yet. | limitation 0.98 | 0.14 | 0.04 | asserted 1.00 |
| s11 | An alternative is building a hybrid system with in vitro neural networks coupled through hardware memristive connections. | future work 0.80 | 0.07 | 0.07 | hedged possibility 0.55 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
One of the challenges of modern neuroscience is creating a "living computer" based on neural networks grown in vitro. Such an artificial device is supposed to perform neurocomputational tasks and interact with the environment when embodied in a robot. Recent studies have identified the most critical challenge, the search for a neural network architecture to implement associative learning. This work proposes a model of modular architecture with spiking neural networks connected by unidirectional couplings. We show that the model enables training a neuro-robot according to Pavlovian conditioning. The robot's performance in obstacle avoidance depends on the ratio of the weights in inter-network couplings. We show that besides STDP, critical factors for successful learning are synaptic and neuronal competitions. We use the recently discovered shortest path rule to implement the synaptic competition. This method is ready for experimental testing. Strong inhibitory couplings implement the neuronal competition in the subnetwork responsible for the unconditional response. Empirical testing of this approach requires a technique for growing neural networks with a given ratio of excitatory and inhibitory neurons not available yet. An alternative is building a hybrid system with in vitro neural networks coupled through hardware memristive connections.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.