Effect of spike-timing-dependent plasticity on neural assembly computing

Eskandari, Elahe; Ahmadi, Majid; Gomar, Shaghayegh

doi:10.1016/j.neucom.2016.01.003

Cited by 10 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, researchers have focused on the development of new learning mechanisms based on neural interactions in the nervous system [16]. Hebbian learning and subsequently spike-timing-dependent plasticity (STDP) learning mechanisms have been favored based on their hypothesized biological evidence for learning in the nervous system and became a key feature of training procedures used in spiking neural networks [41][42]. Although, spike-based back-propagation [43] and deep networks transformed into spiking deep networks [44] have been introduced, they rely on supervised…”

Section: Learning Mechanism (Btdp)mentioning

confidence: 99%

A novel un-supervised burst time dependent plasticity learning approach for biologically pattern recognition networks

Amiri

Jafari‬

Makkiabadi

et al. 2023

Information Sciences

View full text Add to dashboard Cite

Section: Learning Mechanism (Btdp)mentioning

confidence: 99%

A novel un-supervised burst time dependent plasticity learning approach for biologically pattern recognition networks

Amiri

Jafari‬

Makkiabadi

et al. 2023

Information Sciences

View full text Add to dashboard Cite

“…In this regard, based on biological observation, Spatial-STDP affects the transmissions of AMPA and GABA neurotransmitters during the learning process. Similar to Hebbian learning 30 , 31 , STDP and spatial-STDP are learning approach based on biological evidence of nervous system learning. In fact, in spatial-STDP learning procedure, the synaptic weights are updated based on the spike activity of the presynaptic and postsynaptic neurons and the distance between them, and this process continues until the network learn the patterns.…”

Section: Architecture and Learning Mechanism Of The Pattern Recogniti...mentioning

confidence: 99%

Recognizing intertwined patterns using a network of spiking pattern recognition platforms

Amiri

Jafari‬

Makkiabadi

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Artificial intelligence computing adapted from biology is a suitable platform for the development of intelligent machines by imitating the functional mechanisms of the nervous system in creating high-level activities such as learning, decision making and cognition in today's systems. Here, the concentration is on improvement the cognitive potential of artificial intelligence network with a bio-inspired structure. In this regard, four spiking pattern recognition platforms for recognizing digits and letters of EMNIST, patterns of YALE, and ORL datasets are proposed. All networks are developed based on a similar structure in the input image coding, model of neurons (pyramidal neurons and interneurons) and synapses (excitatory AMPA and inhibitory GABA currents), and learning procedure. Networks 1–4 are trained on Digits, Letters, faces of YALE and ORL, respectively, with the proposed un-supervised, spatial–temporal, and sparse spike-based learning mechanism based on the biological observation of the brain learning. When the networks have reached the highest recognition accuracy in the relevant patterns, the main goal of the article, which is to achieve high-performance pattern recognition system with higher cognitive ability, is followed. The pattern recognition network that is able to detect the combination of multiple patterns which called intertwined patterns has not been discussed yet. Therefore, by integrating four trained spiking pattern recognition platforms in one system configuration, we are able to recognize intertwined patterns. These results are presented for the first time and could be the pioneer of a new generation of pattern recognition networks with a significant ability in smart machines.

show abstract

“…As a consequence, the spike-timingdependent plasticity (STDP) mechanism was developed, allowing for online synaptic weight allocation based on the temporal information embedded in the neurons' output spike trains. STDP is a learning approach based on scientific evidence of nervous system learning, similar to Hebbian learning [57][58]. The STDP learning mechanism changes synaptic weights based on presynaptic and postsynaptic neuron spike activity and this process is repeated until the patterns are memorized by the network.…”

Section: Learning Mechanismmentioning

confidence: 99%

Neuromorphic circuit based on the un-supervised learning of biologically inspired spiking neural network for pattern recognition

Nazari

Keyanfar

Hulle

2022

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Effect of spike-timing-dependent plasticity on neural assembly computing

Cited by 10 publications

References 22 publications

A novel un-supervised burst time dependent plasticity learning approach for biologically pattern recognition networks

A novel un-supervised burst time dependent plasticity learning approach for biologically pattern recognition networks

Recognizing intertwined patterns using a network of spiking pattern recognition platforms

Neuromorphic circuit based on the un-supervised learning of biologically inspired spiking neural network for pattern recognition

Contact Info

Product

Resources

About