Hassan Naseri

Jorge Murillo presented our paper titled "CDN-Shifter: Leveraging Spatial Workload Shifting to Decarbonize Content Delivery Networks" at the ACM Symposium on Cloud Computing (ACM SoCC) earlier this week. The paper presents a spatial workload scheduling algorithm called CDN-Shifter for greening CDNs. Read it here: https://lnkd.in/eSxCU-Qh Walid Hanafy David Irwin Ramesh Sitaraman #cloudcomputing #decarbornization

46

📢 Call for Papers: Advances in Learning on Graphs and Information Networks I am thrilled to co-edit a special issue of Electronics (MDPI) with Soumyakant Padhee and Koray Ozcan! We welcome contributions related to graph-structured data and information networks. Please share with your colleagues who have an interest in this topic. Specifically: 🔗 Graph Neural Networks (GNNs) 📊 Graph Embeddings 🌐 Applications: Healthcare, social media, finance, and more ⏳ Dynamic Graph Learning ⚖️ Explainability & Fairness 📅 Submission Deadline: July 15, 2025 More info at the link. #GraphLearning #GNN #MachineLearning #CallForPapers #Research #informationscience

9

Congratulations to Gokce Guven for her paper on X-ray to 3D lung mesh reconstruction, which is accepted to IEEE Access. X2V model architecture employs a neural network to approximate the occupancy function for 3D lung CTs, interpreting each point in space as an occupancy probability. The X2V framework further enhances this process with ViT encoder, densely connected layers and conditional batch normalization, improving the network's ability to reconstruct complex 3D structures of lung CTs. Please check out our paper at the following link: https://lnkd.in/dR5KD9MH #deeplearning

60

1 Comment

🏆 Congratulations to Research Scientist Shiran Dudy (pictured below), Postdoctoral Research Fellow Ibrahim Said Ahmad, and Principal Research Scientist Àgata Lapedriza on their Best Paper Award in Affective Computing and Intelligent Interaction at this year’s #ACII2024 Awards Ceremony! 👏   The group’s paper "Analyzing Cultural Representations of Emotions in LLMs through Mixed Emotion Survey" explores a growing interest in #academia to use #LLMs to simulate and study human behaviors, and how LLMs represent emotions across different cultures.   Read more about their research here: https://bit.ly/4huRYv9 #AI #artificialintelligence #research #tech #generativeAI #genAI #AIresearch #emotions #science

23

2 Comments

Empathy Deception with AI. What's the reality? My chart, attached in the comments, shows how important Rapport is at the base of all kinds of service exchanges and what AI's range is relative to what humans can do. At its basic level, AI can replicate cognitively constructed, intellectualised sympathy. At its most sophisticated this can fool people into thinking the AI is demonstrating empathy because of its 'fidelity of relevance'. However as you rightly say this is not based on actual creation and fostering of emotions in a felt, deep, resonant way. Of course it is an illusion with hidden hallucinations, that, if not managed effectively, will manifest risks to psychological safety and even cause harm.

6

1 Comment

Φ-DVAE: Physics-Informed Dynamical Variational Autoencoders for Unstructured Data Assimilation now published in Journal of Computational Physics

89

1 Comment

It was of great value to attend this enlightening tutorial on the prospective directions of 5/6G applications in virtual and augmented reality, by Mischa Dohler. #IEEE https://lnkd.in/dYzTvsje

42

2 Comments

Call for papers - Electronics | Special Issue : Advances in Quantum Machine Learning @Electronics MDPI https://lnkd.in/e2nGdDHg The scope of this special issue encompasses a broad range of topics within quantum machine learning, including but not limited to the following: Quantum algorithms for classification, regression, clustering, and optimization; Quantum neural networks and quantum-enhanced deep learning architectures; Quantum-enhanced feature selection and dimensionality reduction; Quantum data encoding, representation, and processing techniques; Quantum-inspired AI algorithms and their applications across various domains, including energy, finance, cybersecurity, 6G, healthcare, chemistry, and beyond; Quantum robotics and control systems; Quantum annealing and high-performance computing (HPC) for AI; AI for quantum compilers, error correction, and mitigation; AI for quantum gate synthesis, algorithms, and circuit optimization and design; AI for quantum circuit mapping and hardware design; AI for quantum resource allocation. We welcome submissions for researchers in these areas.

33

Video of our recent Genetic and Evolutionary Computation Conference (GECCO) talk on "Survival-LCS: A Rule-based #MachineLearning Approach to Survival Analysis". Awarded best paper in the Evolutionary Machine Learning Track. https://lnkd.in/gtfuqeut

26

A Tale of Programming Languages - The impact of Quantum Computing ( https://lnkd.in/ebYtX2zA )

2

Read #RNCP latest paper accepted for publication in IEEE Journal of Quantum Electronics that introduces the use of four-wave mixing (FWM) in photonic neuromorphic computing. FWM is a complex nonlinear process attributed to Kerr effect and can be triggered in highly nonlinear fibers and silicon photonics nano-waveguides. The paper shows how it can be leveraged to provide arbitrary nonlinear activation functions and complex polynomial processing as an extreme learning machine modality in specific nonlinear tasks with very high performance. Many thanks to Kostas Sozos, Stavros Deligiannidis and my colleague Charis Mesaritakis, Ph.D. This work was funded by our HFRI project #NOOKHFRI. #neuromorphiccomputing #photonics #nonlinearoptics

46

A new Journal paper has been published in Computing Journal (Q1 with IF 3.7) published by Springer Nature Group, with Dr Lamis Al-Qora'n, PhD. and Ahmad Zayed. https://lnkd.in/ewScijRx In this paper, we are looking to apply chaos engineering scenarios to cloud-native applications. The study introduced two native fault injection techniques and empirically provided analysis of real-world scenarios. The results showed a reduction in performance and an increase in latency with injecting delays. However, faults and availability problems appeared at a particular delay, highlighting the importance of using chaos engineering to assess the dependability of cloud-native applications and find unpredicted failures. This paper is part of research supported by the an RDF fund by Keele University. #cloud_native #dependability #performance #cloud_computing

34

7 Comments

A new lecture in the Course: "Introduction to Quantum Computing", has been published: https://lnkd.in/dAbjGRHk Lecture 14: The CHSH Game In this lecture we introduce nonlocal games, and in particular the CHSH game. It is one of the Bell tests that show the proper difference between quantum information and the counterpart classical realm. We game protocol is defined and we show that any classical strategy has at most 75% of winning. However, by going quantum, particularly, sharing and entanglement-bit between Alice and Bob, an 85% chance of winning is achieved. The instruction language is Arabic, however, all the material, slides, examples, definitions, concepts, etc., are all given in English.

10

Quantum Full-Duplex Communications - if you are interested in this area, please check our newly published paper on IEEE Journal on Selected Areas in Communications (JSAC). Fakhar Zaman Uman Khalid https://lnkd.in/e-B3Qazx In this work, we propose the protocols that enable simultaneous classical and quantum information exchange using counterfactual quantum communication principles. These innovations enhance communication security and efficiency, potentially impacting next-generation networks like 6G. By employing advanced quantum concepts such as entanglement and counterfactuality, the study demonstrates practical applications of theoretical quantum mechanics. Overall, this research provides significant foundational work for integrating quantum capabilities into future communication technologies, enhancing both security and throughput.

70

1 Comment

🚀 Exploring Extrinsic Hallucinations in LLMs! 🚀 The article delves into the causes and solutions for hallucinations in large language models (LLMs). 🌟Key highlights: - Causes of Hallucinations: Addressing issues in pre-training data and the challenges of fine-tuning with new knowledge. - Detection Methods: Utilizing techniques like retrieval-augmented evaluation and sampling-based detection to identify hallucinations. - Anti-Hallucination Techniques: Implementing strategies such as Retrieval-Augmented Generation (RAG), fine-tuning for factuality, and employing retrieval methods to enhance accuracy. https://lnkd.in/g3j5kU5b For more updates, follow Rohit Agarwal! #AI #LLMs #MachineLearning #TechInnovation #DataScience #ModelAccuracy #FactualAI #HallucinationDetection

4

Happy to share our latest paper titled "Text-RGNNs: Relational Modeling for Heterogeneous Text Graphs" published in IEEE Signal Processing Letters!   Building on the foundational Text-Graph Convolutional Network (TextGCN), which represents corpora with heterogeneous text graphs, we addressed a key limitation: GCNs are inherently designed to operate within homogeneous graphs, potentially limiting their performance. To overcome this, based on relational graph neural networks (RGNNs), we introduced Text-RGNNs, assigning dedicated weight matrices to each relation using heterogeneous GNNs for more nuanced and effective modeling. Our extensive experimentation shows that Text-RGNNs significantly outperform existing state-of-the-art models, especially with complete labeled nodes and minimal labeled training data, achieving up to 10.61% improvement in evaluation metrics!   Check out the paper for more details! Paper: https://lnkd.in/dxDQuMBg Code: https://lnkd.in/dz4metCR #GSP #GNN #NLP #TextClassification #Transformer #RGNN #IEEE

73

Here is our new paper accepted in Neurocomputing journal. SITU: Stochastic input encoding and weight update thresholding for efficient memristive neural network in-situ training The Analog-to-Digital Converter (ADC) sensing and conductance update are the most power-demanding processes in the in-situ training of memristive neural networks. In this work, we propose a new thresholded weight update method in conjunction with stochastic input encoding to reduce the ADC sensing requirement and weight updates. This leads to better power and area efficiency for simple neural network models developed in situ on memristive crossbars. This is an interesting research work by Xuening Dong and collaboration between University of Toronto, James Cook University , and York University. https://lnkd.in/gY4-GgtC

58

1 Comment