IEEE’s Post

Is the future of computing in quantum solutions? Given the real processing power of the human brain, growing brains in a lab and networking could give a low footprint processing powerplant. Ethical issues aside, biological systems could offer long term solutions. Same opportunity of networked neural links. Interesting where the research is heading. The brains only consumes 20 watts.

Check out our recent paper solving PDEs on neuromorphic architectures using physics-informed neural networks (PINNs)! In this paper we discuss how a trained PINN is first converted to a spiking neural network (SNN). To complete the migration to neuromorphic hardware, we quantize floating point values in the network. The results section explores the accuracy, throughput, and power consumption tradeoffs using Intel's Loihi 2 platform. While in an early stage, the results show the promise of how these novel hardware systems can be utilized to solve problems in scientific machine learning. Stay tuned! This was a great multi-institution SEA-CROGS collaboration with Brad Theilman (Sandia), Qian Zhang (Brown), Adar Kahana, Brad Aimone, Nat Trask, and George Karniadakis. Thanks all!

We are happy to share that our two recent papers, 'Predicting Failures in Induction Motors Used in Manufacturing Machinery Using Unsupervised Learning' and 'Evaluation of Artificial Neural Network Architectures for Intrusion Detection in Data Networks,' were presented at the 2nd International Engineering Research Symposium 2024 (IERS 2024). A special thanks to my co-author, Shamila Kulatunga, for presenting our work. #ResearchInnovation #MachineLearning #ArtificialIntelligence #UnsupervisedLearning #NeuralNetworks #IERS2024 #ManufacturingTechnology #DataSecurity #AcademicResearch #InnovationInTech #IndustrialAutomation

Explore the editor's pick, "Neuromorphic Computing with Address-Event-Representation using Time-to-Event Margin Propagation". 📝 Authored by: Madhuvanthi Srivatsav R; Shantanu Chakrabartty; Chetan Singh Thakur Volume: 13, Issue: 4, December 2023 In this paper, the authors show how address-event-representation (AER) can be used for implementing a processing-in-interconnect paradigm (2), similar to the concept of dendritic computing. The key novelty in this work is the time-to-event margin propagation (TEMP) principle that can exploit computational primitives like causality, sorting, and triggering which can be naturally mapped onto the physics of an interconnect (physical or virtual) and enable event-based communications. The authors demonstrate how TEMP-based spiking neural networks can produce a rich repertoire of spatio-temporal dynamics that can be used for building energy-efficient AI hardware. 🔗 Read more on IEEE Xplore: https://loom.ly/Zz4IFlo Congratulations to the authors for being selected among the top papers of this issue! #IEEE #IEEEXplore #JETCAS #ReadMore #CircuitsandSystems #graphicalabstract

The neural network structure of artificial intelligence algorithms, each node represents a neuron, they work together to complete complex computing tasks

Happy to share that our paper titled 𝑨𝒏 𝑼𝒏𝒔𝒖𝒑𝒆𝒓𝒗𝒊𝒔𝒆𝒅 𝑺𝒄𝒊𝒆𝒏𝒕𝒊𝒇𝒊𝒄 𝑴𝒂𝒄𝒉𝒊𝒏𝒆 𝑳𝒆𝒂𝒓𝒏𝒊𝒏𝒈 𝑨𝒍𝒈𝒐𝒓𝒊𝒕𝒉𝒎 𝒇𝒐𝒓 𝑨𝒑𝒑𝒓𝒐𝒙𝒊𝒎𝒂𝒕𝒊𝒏𝒈 𝑫𝒊𝒔𝒑𝒍𝒂𝒄𝒆𝒎𝒆𝒏𝒕 𝒐𝒇 𝑶𝒃𝒋𝒆𝒄𝒕 𝒊𝒏 𝑴𝒂𝒔𝒔-𝑺𝒑𝒓𝒊𝒏𝒈-𝑫𝒂𝒎𝒑𝒆𝒓 𝑺𝒚𝒔𝒕𝒆𝒎𝒔, coauthored by Prof. Snehashish Chakraverty and Mr. Sandeep Kumar has been accepted to publish in IEEE Access (Q1, IF: 3.4, SCIe) journal. In this paper, we focus on applying Artificial Neural Networks, particularly Physics-Informed Neural Networks (PINNs), to various dynamical problems. Yesterday, Dr. John Hopfield (creator of the Hopfield Neural Network) and Dr. Geoffrey Hinton (often referred to as the "Father of Artificial Neural Networks") were nominated for the Nobel Prize for their groundbreaking contributions to the field of Artificial Neural Networks. This recognition underscores the promising future of research in this area. Please find our paper here: (https://lnkd.in/gPwa8NVE). #PhysicsInformedMachineLearning  #ANN 

Alhamdulillah, our first paper has been accepted at the 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT 2024), and it will be published on IEEE Xplore. Paper Name: Unveiling Predictive Factors in Apple Quality: Leveraging LIME, SHAP, and the Synergy of Machine Learning Models and Artificial Neural Networks (Rituparna Chowdhury, Rudra Das, Md.Hamid Hosen, Arnob Saha, Sadia Nawar)

This year’s Nobel Prize in Physics has been awarded to John J. Hopfield and Geoffrey E. Hinton for their revolutionary work on artificial neural networks, a field that continues to shape machine learning. Their pioneering research, which laid the foundation for today’s powerful machine learning techniques, focused on using physics-inspired methods to develop models capable of storing and reconstructing patterns in data. Hopfield’s associative memory and Hinton’s method for autonomously finding properties in data have been instrumental in advancing machine learning applications. At BosonQ Psi (BQP), we’re also leveraging quantum computing to enhance machine learning capabilities. Our focus lies in applying quantum machine learning (#QML) to address complex challenges like computational fluid dynamics (#CFD) and computer vision. As the field of machine learning continues to evolve, we’re excited about the potential of quantum computing to unlock new possibilities and accelerate progress.  #Quantumcomputing #qml #nobelprize24

✨Day 28 Of #Quantum30 challenge : Active Break Key takeaways from 4th week: 1. This week comprised of exploring various examples of Quantum Neural Network (QNN) using Qiskit and PennyLane. 2. Understanding the basics of Quantum Image Processing (QIP) and especially two models for representation of digital images on quantum computers viz. Enhanced NEQR (ENEQR) and Enhanced FRQI (EFRQI). 3. Further learnt about QML using Amazon Braket Hybrid Jobs which unites classical and quantum computing thus enabling effective solutions for complex problems. #QuantumComputingIndia #quantumcomputing #quantumtechnology

Thrilled to announce our recent publication in the Hinweis Second International Conference on Advances in Information, Telecommunication and Computing (AITC)! 🎉 I extend my deepest gratitude to my guide and Co-Author, Dr. Somnath Sinha, along with Dr. NEHA SINGHAL and Dr Sudhakar T , whose unwavering support and insightful contributions made this achievement possible. It's truly a testament to our collective dedication and teamwork. Our paper, titled "Enhancing Movie Genre Classification through  Emotional Intensity Detection: An Improvised Machine Learning Approach" is a culmination of cutting-edge research in the realm of Emotion Detection. We developed a sequential neural network model to identify facial emotions and correlate them with movie genres. Through innovative image processing algorithms, we delve into the forefront of Emotion Detection, showcasing the potential of neural network models in this domain. Excited to share our insights and contribute to the discourse on Emotion Detection and Genre Classification! 📚🔍 #ResearchPublication #EmotionDetection #GenreClassification #NeuralNetworks #Innovation