Special Session on
Memristor-Based Neural Networks: A Bridge from Device to Artificial Intelligence
Aim and Scope
The future applications of cutting-edge neural networks, including deep neural networks (DNNs) and spiking neural networks (SNNs), as well as possible methods for getting over the physical constraints of memristor-based neural networks.
With the fast advancement of cloud computing, Internet of Things applications, big data analytics, artificial intelligence, and other fields, memristor devices and related hardware systems are expected to address large-scale data calculations with low power consumption and compact chip area. Artificial intelligence has gained prominence since the turn of the twenty-first century in several fields. One such field is memristor-based artificial neural network technology, which is anticipated to surpass von Neumann's constraints in simulating the human brain by facilitating powerful parallel computing and effective data processing, thereby representing a significant advancement towards the next generation of artificial intelligence. The memristor, a novel nanodevice based on resistance value fluctuation, is one of the most promising circuit elements of the post-Moore period. It has important applications in non-volatile information storage and obsessive progressiveness in highly integrated circuits. Memristors can imitate brain synapses and form neural networks, making them useful for AI system development. Von Newman-based computers struggle to handle and store “big data.” The creation of an artificial neural network (ANN) that can process and store data similarly to the human brain is one of the most promising answers to this problem as shown in Fig. 1. Instead of CMOS components, ANNs use memristors, which closely mirror the brain's electrical and optical responses, to extend Moore's law.
Fig. 1: Analogy between memristor-based artificial neural networks and the synapse-based nerve net
The memristor can function as an electrical junction and may also be used in the development of artificial neural networks. Recent developments have shown that memristors can perform many synaptic tasks, notably in learning and memory. The primary memristor-based neural networks with differing information coding are ANNs and SNNs. ANN optimizes computing efficiency in data-intensive operations, whereas SNN simulates biological neural networks with peak-time encoded neuron values to maximize power efficiency. Classical ANN hardware can only execute multiplication, addition, and activation, which CMOS circuits like GPUs can do. The CMOS circuit is scalable, but it cannot match the neuromorphic simulation of the ANN for neural networks with many computational parameters. Numerous topology-learning techniques use ANN software and hardware.
Memristor Applications in Artificial Intelligence (AI) and Neuromorphic Computing:
- Neuromorphic Computing
- Efficient Learning Algorithms
- Pattern Recognition
- Spiking Neural Networks
- Energy-Efficient AI Systems
- Cognitive and Edge Computing
Paper Submission
Potential authors may submit their manuscripts for presentation consideration through ICETCI 2024 submission system electronically at https://edas.info/N31894 , following the conference guidelines. All submissions will go through peer review process. To submit your paper to this special session, you have to choose our special session title on the submission page.
Important Dates
| Paper submission deadline: | Apr 15, 2024 |
| Paper acceptance notification date: | Jun 20, 2024 |
| Final paper submission and early registration deadline: | Jun 30, 2024 |
Organizers
Dr. Niranjan Raj
Dr. Niranjan Raj is currently working as an Assistant Professor in the Department of Electrical and Electronics Engineering, Birla Institute of Technology and Science Pilani, Hyderabad. He received his bachelor’s degree in Electronics & Communication Engineering, from the Rajeev Gandhi Proudyogiki Vishwavidyalaya, Bhopal, India, and master’s degree in Electronics and Communication Engineering with a specialization in VLSI from the National Institute of Technology Meghalaya, India, respectively in 2013 and 2016. He completed his Ph.D. degree in Microelectronics and VLSI from the Indian Institute of Technology, Dhanbad, India in 2022. He is a recipient of the National Post-Doctoral Fellowship from the Science and Engineering Research Board, Government of India. Presently, he worked as a Postdoctoral Researcher in the NeuRonics lab, at the Department of Electronic Systems Engineering, Indian Institute of Science, Bangalore, India. He was a recipient of the Ministry of Human Resource Department (M.H.R.D.) Scholarship for Masters and Doctoral Study. His current research is focused on the Modelling of Memristive devices, integrated circuits, Physical verification of circuits, and Neuromorphic computing. He served as a Reviewer of journals, such as the IEEE Transactions on Very Large-Scale Integration (VLSI) Systems, Electronics Letters, International Journal of Electronics, International Journal of Electronics and Communication (AEU), Elsevier, Circuits, Systems, and Signal Processing, Arabian Journal for Science and Engineering, and Electrical Engineering: Springer Nature. He has authored more than 16 international peer-reviewed journals and conference proceedings publications in reputed journals.
Dr. Sagar
Dr. Sagar is currently working as an Assistant Professor in the Department of Electrical and Electronics Engineering, at ICFAI University, Hyderabad. He received his bachelor’s degree in Electronics & Communication Engineering, from the College of Engineering and Technology (CET), Belgaum, India, and master’s degree in Electronics and Communication Engineering with a specialization in VLSI from the UVCE Government Engineering College, Bangalore University, Bengaluru. He completed his Ph.D. degree in VLSI and Mixed-mode Analog Circuit Design from the Indian Institute of Technology, Dhanbad, India in 2023. He was a recipient of the Ministry of Human Resource Department (M.H.R.D.) Scholarship for Masters and Doctoral Study. His current research is focused on the Modelling of Memristive devices, integrated circuits, fractional System design, and Neuromorphic computing. He served as a Reviewer of journals, such as the IEEE Transactions on Very Large-Scale Integration (VLSI) Systems, IEEE ACCESS, Electronics Letters, International Journal of Electronics, and Arabian Journal for Science and Engineering, and Electrical Engineering: Springer Nature. He has authored more than 13 international peer-reviewed journals and conference proceedings publications in reputed journals.