Evolving Spiking Neural Networks of artificial creatures using Genetic Algorithm

Eskandari, Elahe; Ahmadi, Arash; Gomar, Shaghayegh; Ahmadi, M.; Saif, Mehrdad

doi:10.1109/ijcnn.2016.7727228

Cited by 11 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A framework for the neuroevolution of SNNs and topology growth with genetic algorithms is proposed by Schaffer [16], with the goal of pattern generation and sequence detection. Eskandari et al [17] propose a similar framework for artificial creature control, where the evolutionary process modifies and inherits the network topology and the SNN weights to perform a given task.…”

Section: Related Workmentioning

confidence: 99%

A Conceptual Bio-Inspired Framework for the Evolution of Artificial General Intelligence

Pontes-Filho,

Nichele

2019

Preprint

View full text Add to dashboard Cite

In this work, a novel framework for the emergence of general intelligence is proposed, where agents evolve through environmental rewards and learn throughout their lifetime without supervision, i.e., self-supervised learning through embodiment. The chosen control mechanism for agents is a biologically plausible neuron model based on spiking neural networks. Network topologies become more complex through evolution, i.e., the topology is not fixed, while the synaptic weights of the networks cannot be inherited, i.e., newborn brains are not trained and have no innate knowledge of the environment. What is subject to the evolutionary process is the network topology, the type of neurons, and the type of learning. This process ensures that controllers that are passed through the generations have the intrinsic ability to learn and adapt during their lifetime in mutable environments. We envision that the described approach may lead to the emergence of the simplest form of artificial general intelligence.

show abstract

Section: Related Workmentioning

confidence: 99%

A Conceptual Bio-Inspired Framework for the Evolution of Artificial General Intelligence

Pontes-Filho,

Nichele

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…In this work, we aim at generating fully automatically characters drawn by humans, especially children. To solve the problem of the many possible animations for a given drawing, we take inspiration from evolutionary robotics [7], and use a neural network to control the skeleton animation within a 2-D physics-based simulator [3]. As in Feng et al [4], we automatically extract the skeleton from the drawing using a morphological thinning operation [6], but where the latter asks the user to select parts that belong together, we use a set of heuristics to fully automatically generate a skeleton.…”

Section: Related Workmentioning

confidence: 99%

“…We weight their contribution using a function of the distance through a Gaussian kernel. We export the result to the glTF binary format 3 .…”

Section: Vertex Skinningmentioning

confidence: 99%

Towards automatic drawing animation using physics-based evolution

Lingens

Sumner

Magnenat

2020

Proceedings of the 2020 ACM Interaction Design and Children Conference: Extended Abstracts

View full text Add to dashboard Cite

We demonstrate a system to automatically animate hand-drawn characters. Starting with skeleton extraction, meshing and vertex skinning, our system simulates characters using a neural network in a physics-based environment. Using an evolutionary algorithm, it searches for networks that move characters far while keeping a good posture. We validated the system through a user study with 26 participants. For most drawings (60 %), they felt satisfied with the generated animation, and in 76 % of cases, they wished to draw and animate additional characters. The participants reported mostly positive emotions after seeing the animations. Only a minority had feelings of strangeness or had negative emotions. This work demonstrates the possibility of creating an automated 2-D character animation system making little assumption on what is drawn. We believe that this work can enable more children to engage in creative play and explore their imagination.

show abstract

“…This is primarily due to the use of spikes for information transmission, which does not naturally lend itself toward being used with backpropagation. To circumvent this challenge, a wide variety of learning algorithms have been proposed including Spike-Timing Dependent Plasticity (STDP) (Masquelier et al, 2009;Bengio et al, 2017;Kheradpisheh et al, 2018;Mozafari et al, 2018), ANN to SNN conversion methods (Diehl et al, 2015;Rueckauer et al, 2017;Hu et al, 2018), Eligibility Traces (Bellec et al, 2020), and Evolutionary Strategies (Pavlidis et al, 2005;Carlson et al, 2014;Eskandari et al, 2016;Schmidgall, 2020). However, a separate body of literature enables the use of backpropagation directly with SNNs typically through the use of surrogate gradients (Bohte et al, 2002;Sporea and Grüning, 2012;Lee et al, 2016;Shrestha and Orchard, 2018).…”

Section: Introduction and Related Workmentioning

confidence: 99%

SpikePropamine: Differentiable Plasticity in Spiking Neural Networks

et al. 2021

View full text Add to dashboard Cite

The adaptive changes in synaptic efficacy that occur between spiking neurons have been demonstrated to play a critical role in learning for biological neural networks. Despite this source of inspiration, many learning focused applications using Spiking Neural Networks (SNNs) retain static synaptic connections, preventing additional learning after the initial training period. Here, we introduce a framework for simultaneously learning the underlying fixed-weights and the rules governing the dynamics of synaptic plasticity and neuromodulated synaptic plasticity in SNNs through gradient descent. We further demonstrate the capabilities of this framework on a series of challenging benchmarks, learning the parameters of several plasticity rules including BCM, Oja's, and their respective set of neuromodulatory variants. The experimental results display that SNNs augmented with differentiable plasticity are sufficient for solving a set of challenging temporal learning tasks that a traditional SNN fails to solve, even in the presence of significant noise. These networks are also shown to be capable of producing locomotion on a high-dimensional robotic learning task, where near-minimal degradation in performance is observed in the presence of novel conditions not seen during the initial training period.

show abstract

Evolving Spiking Neural Networks of artificial creatures using Genetic Algorithm

Cited by 11 publications

References 15 publications

A Conceptual Bio-Inspired Framework for the Evolution of Artificial General Intelligence

A Conceptual Bio-Inspired Framework for the Evolution of Artificial General Intelligence

Towards automatic drawing animation using physics-based evolution

SpikePropamine: Differentiable Plasticity in Spiking Neural Networks

Contact Info

Product

Resources

About