Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities

Pietrzak, Paweł; Szczęsny, Szymon; Huderek, Damian; Przyborowski, Łukasz

doi:10.3390/s23063037

Cited by 15 publications

(3 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their computational power surpasses the abilities of ANN in that they can process spike trains over time decoding temporal information. Moreover, implementation of SNNs even on large scales is not difficult ( Cessac et al, 2010 ; Pietrzak et al, 2023 ).…”

Section: Information Processing In Brain: Theoretical Conceptsmentioning

confidence: 99%

The computational power of the human brain

Gebicke-Haerter

2023

Front. Cell. Neurosci.

View full text Add to dashboard Cite

At the end of the 20th century, analog systems in computer science have been widely replaced by digital systems due to their higher computing power. Nevertheless, the question keeps being intriguing until now: is the brain analog or digital? Initially, the latter has been favored, considering it as a Turing machine that works like a digital computer. However, more recently, digital and analog processes have been combined to implant human behavior in robots, endowing them with artificial intelligence (AI). Therefore, we think it is timely to compare mathematical models with the biology of computation in the brain. To this end, digital and analog processes clearly identified in cellular and molecular interactions in the Central Nervous System are highlighted. But above that, we try to pinpoint reasons distinguishing in silico computation from salient features of biological computation. First, genuinely analog information processing has been observed in electrical synapses and through gap junctions, the latter both in neurons and astrocytes. Apparently opposed to that, neuronal action potentials (APs) or spikes represent clearly digital events, like the yes/no or 1/0 of a Turing machine. However, spikes are rarely uniform, but can vary in amplitude and widths, which has significant, differential effects on transmitter release at the presynaptic terminal, where notwithstanding the quantal (vesicular) release itself is digital. Conversely, at the dendritic site of the postsynaptic neuron, there are numerous analog events of computation. Moreover, synaptic transmission of information is not only neuronal, but heavily influenced by astrocytes tightly ensheathing the majority of synapses in brain (tripartite synapse). At least at this point, LTP and LTD modifying synaptic plasticity and believed to induce short and long-term memory processes including consolidation (equivalent to RAM and ROM in electronic devices) have to be discussed. The present knowledge of how the brain stores and retrieves memories includes a variety of options (e.g., neuronal network oscillations, engram cells, astrocytic syncytium). Also epigenetic features play crucial roles in memory formation and its consolidation, which necessarily guides to molecular events like gene transcription and translation. In conclusion, brain computation is not only digital or analog, or a combination of both, but encompasses features in parallel, and of higher orders of complexity.

show abstract

Section: Information Processing In Brain: Theoretical Conceptsmentioning

confidence: 99%

The computational power of the human brain

Gebicke-Haerter

2023

Front. Cell. Neurosci.

View full text Add to dashboard Cite

show abstract

“…Due to the use of discrete events in processing, SNN compute a single response across multiple time steps, making them less efficient on standard synchronous computer hardware but potentially more effective on specialized neuromorphic hardware [ 17 ]. This specialized hardware, comprising asynchronous and event-driven circuits, guides the design of building blocks for hardware solutions, particularly advantageous for robotic platforms [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

A Novel Robotic Controller Using Neural Engineering Framework-Based Spiking Neural Networks

Marrero,

Kern,

Urrea

2024

Sensors

View full text Add to dashboard Cite

This paper investigates spiking neural networks (SNN) for novel robotic controllers with the aim of improving accuracy in trajectory tracking. By emulating the operation of the human brain through the incorporation of temporal coding mechanisms, SNN offer greater adaptability and efficiency in information processing, providing significant advantages in the representation of temporal information in robotic arm control compared to conventional neural networks. Exploring specific implementations of SNN in robot control, this study analyzes neuron models and learning mechanisms inherent to SNN. Based on the principles of the Neural Engineering Framework (NEF), a novel spiking PID controller is designed and simulated for a 3-DoF robotic arm using Nengo and MATLAB R2022b. The controller demonstrated good accuracy and efficiency in following designated trajectories, showing minimal deviations, overshoots, or oscillations. A thorough quantitative assessment, utilizing performance metrics like root mean square error (RMSE) and the integral of the absolute value of the time-weighted error (ITAE), provides additional validation for the efficacy of the SNN-based controller. Competitive performance was observed, surpassing a fuzzy controller by 5% in terms of the ITAE index and a conventional PID controller by 6% in the ITAE index and 30% in RMSE performance. This work highlights the utility of NEF and SNN in developing effective robotic controllers, laying the groundwork for future research focused on SNN adaptability in dynamic environments and advanced robotic applications.

show abstract

“…The development of AI is growing fast due to the availability of vast amounts of data, making it easy to train machines to learn and make decisions (Duan et al, 2019). The exponential growth of computing power also characterises the growth in AI; thus, developing specialised hardware such as graphics processing units (GPUs) and tensor processing units (TPUs) has accelerated AI training and inference process (Khan et al, 2021;Cowls et al, 2021;Pietrzak et al, 2023). Today, AI is emerging as a transformative force with its applications spanning various industries, such as healthcare and medical surgery (Hashimoto et al, 2020;Gamble, 2020).…”

Section: Introductionmentioning

confidence: 99%

Leveraging on Chatgpt, an Artificial Intelligence (AI) Tool to Transform Examination Writing in Higher Education

Atieku-Boateng,

Osei,

Aryee

et al. 2024

Preprint

View full text Add to dashboard Cite

Purpose The study explored how ChatGPT could transform examination writing in higher education. The research question was: How can the AI tool ChatGPT help transform examination writing in higher education? The study interviewed the chatbot (ChatGPT) by way of "prompt engineering" to test if it has the potential to achieve the following: (1) Generate varied questions on a subject matter of the same level of difficulty, (2) Generate varied questions on a subject matter with case scenarios, (3) Generate varied questions on a subject matter that requires critical thinking, (4) Generate varied questions on a subject matter that takes into consideration the diverse needs and backgrounds of students and (5) Streamline assessment process. These objective tests were to explore the diverse ways the chatbot could assist in the examination process. Despite the academic concerns surrounding students' use of ChatGPT, the study's findings seek to stimulate discussion on the potentially significant benefits ChatGPT offers to the educational sector if it is effectively implemented. Approach/Design/Method Through "prompt engineering", the study interviewed ChatGPT to test it on the five (5) objectives. Subject area lecturers and exam moderators reviewed questions as well as marking schemes generated by the chatbot to ensure accuracy and appropriateness. Findings ChatGPT was able to generate varied questions of the same difficulty level on the same given content and generated questions with case scenarios. The questions generated also required critical thinking; ChatGPT produced questions considering students' diverse needs and backgrounds. Finally, it could streamline the assessment process as well. However, ChatGPT required specific human guidance to shape the questions. Also, the examiner or the educator needed to double-check the accuracy of the questions generated. Additionally, it was discovered that the version of ChatGPT used was limited in subject areas that required graphics and figures. Research Limitations/Implications The study found that ChatGPT is effective with text-like tasks but is limited in areas that require graphics and figures (for the version used), which may be needed in some fields of study. It also meant that responses only had to be in text for the Chatbot to award scores based on the assessment criteria. Notwithstanding the limitations, ChatGPT can become an excellent tool for assisting educators in assessing students, thereby transforming examination writing in higher education. The originality of the study Research on ChatGPT is an emerging one. The study is novel, as this area is still being explored. This paper will serve as one of the early research works that provide educators and policymakers with knowledge of leveraging ChatGPT to transform examination writing.

show abstract

Overview of Spiking Neural Network Learning Approaches and Their Computational Complexities

Cited by 15 publications

References 63 publications

The computational power of the human brain

The computational power of the human brain

A Novel Robotic Controller Using Neural Engineering Framework-Based Spiking Neural Networks

Leveraging on Chatgpt, an Artificial Intelligence (AI) Tool to Transform Examination Writing in Higher Education

Contact Info

Product

Resources

About