the proceedings contain 98 papers. the special focus in this conference is on Geometric Science of Information. the topics include: Geodesics and Curvature of the Quotient-Affine Metrics on Full-Rank Co...
ISBN:
(纸本)9783030802080
the proceedings contain 98 papers. the special focus in this conference is on Geometric Science of Information. the topics include: Geodesics and Curvature of the Quotient-Affine Metrics on Full-Rank Correlation Matrices;parallel Transport on Kendall Shape Spaces;diffusion Means and Heat Kernel on Manifolds;a Reduced Parallel Transport Equation on Lie Groups with a Left-Invariant Metric;currents and K-functions for Fiber Point Processes;q-Information Geometry of systems;group Actions and Monotone Metric Tensors: the Qubit Case;quantum Jensen-Shannon Divergences Between Infinite-Dimensional Positive Definite Operators;towards a Geometrization of Quantum Complexity and Chaos;finite Sample Smeariness on Spheres;hunt’s Colorimetric Effect from a Quantum Measurement Viewpoint;the Herglotz Principle and Vakonomic Dynamics;structure-Preserving Discretization of a Coupled Heat-Wave System, as Interconnected Port-Hamiltonian systems;examples of Symbolic and Numerical Computation in Poisson Geometry;new Directions for Contact Integrators;space-Time thermo-Mechanics for a Material Continuum;entropic Dynamics Yields Reciprocal Relations;gibbs States on Symplectic Manifolds with Symmetries;gaussian Distributions on the Space of Symmetric Positive Definite Matrices from Souriau’s Gibbs State for Siegel Domains by Coadjoint Orbit and Moment Map;on Gaussian Group Convex Models;gaussian Distributions on Riemannian Symmetric Spaces in the Large N Limit;Exponential-Wrapped Distributions on SL (2, C) and the Möbius Group;information Geometry and Hamiltonian systems on Lie Groups;multisymplectic Variational Integrators for Fluid Models with Constraints;metriplectic Integrators for Dissipative Fluids;from Quantum Hydrodynamics to Koopman Wavefunctions I;From Quantum Hydrodynamics to Koopman Wavefunctions II;the Fisher Information of Curved Exponential Families and the Elegant Kagan Inequality;continuous Wavelet Transforms for Vector-Valued Functions;entropy Under Disintegrations.
the advent of Internet of things (IoT) technology has created new opportunities for instructors and students to improve the classroom experience. this paper describes a method for creating an IoT-based smart classroom...
详细信息
To strengthen the safety protection of personnel in deep water dangerous areas such as reservoirs and rivers, Relying on the technical characteristics of 5G network technology, such as high speed, low delay, high band...
详细信息
the proceedings contain 21 papers. the topics discussed include: generating a robot framework test script for web application based on database constraints;time-locked free trial strategy choice of duopoly software ve...
ISBN:
(纸本)9798400717543
the proceedings contain 21 papers. the topics discussed include: generating a robot framework test script for web application based on database constraints;time-locked free trial strategy choice of duopoly software vendors considering consumers’ personal internal preferences and network externalities;assessing usability and user experience in E-Pondo: a path to improved interaction design;an empirical evaluation of method signature similarity in java codebases;empirical studies on failure prediction for distributed systems based on feature selection;adaptive and effective data hiding scheme for AMBTC compression codes;and comments on a lightweight authentication and key agreement framework for smart grids.
Analog computing-in-memory (CIM) macro has been widely used in various machine learning (ML) applications, which parallelly perform energy- and area-efficient matrix-vector multiplication (MVM) operations. Compared wi...
详细信息
ISBN:
(纸本)9798350387186;9798350387179
Analog computing-in-memory (CIM) macro has been widely used in various machine learning (ML) applications, which parallelly perform energy- and area-efficient matrix-vector multiplication (MVM) operations. Compared with digital CIM, analog CIM has shown great efficiency on multi-bit MVM computations. However, the analog approaches accumulate the MVM results on the voltage domain, different accumulation lengths and data sparsity cause distinct signal swing degradation and variation. Hence, the analog-to-digital converter (ADC) readout circuit requires more power and area to trade off withthe noise and comparator offset. In this paper, we proposed a partial sum boosting (PSB) method to give 4.6x to 22.8x signal swing enhancement for multi-bit MVM, which mitigates severe ADC overhead for analog CIM. Furthermore, multi-bit 5T-SRAMs with diverse voltage supplies realize multi-bit uniform/non-uniform sign- and-magnitude (SNM) weight representation and save up to 38.8x SRAMs static power dissipation. the chip was fabricated in 28nm CMOS technology and measured a throughput density of 89.04 TOPS/ mm(2) and energy efficiency of 219.5 TOPS/W under 3-bit activation, 4-bit SNM weight with no truncation 5-bit partial sum readout condition.
the proceedings contain 41 papers. the special focus in this conference is on Artificial Intelligence and Applications. the topics include: Gradient Reduction Convolutional Neural Network Policy for Financial Dee...
ISBN:
(纸本)9783031866227
the proceedings contain 41 papers. the special focus in this conference is on Artificial Intelligence and Applications. the topics include: Gradient Reduction Convolutional Neural Network Policy for Financial Deep Reinforcement Learning;an Investigation of Methods for Improving Spatial Invariance of Convolutional Neural Networks for Image Classification;a Review of Uncertainty Quantification in Convolutional Neural Networks;Explainable AI for SQL Grading: A Practical Approach with Multi-task CNNs;exploring Data Augmentation and Stochastic Weight Averaging as an Alternative to Adversarial Training of Deep Neural Networks;Parameterized Model for Fork Antenna Design in UWB Band Using Fully Connected Artificial Neural Networks;driving Planner for Freight Trains Using Reinforcement Learning;fraud Detection Using Machine Learning Models and Encryption Techniques;federated Learning with Frequency Estimation for Smart Meter systems;automatic Labeling of Computer Vision Data Using Self-Supervised Learning;Pruning and Optimizing Large Language Models in an Era of GPU Scarcity;detecting Hallucinations in Large Language Model Generation: A Token Probability Approach;Leveraging Data Augmentation and Large Language Models for Enhanced COVID-19 Tweet Classification;taming Large Language Models for Healthcare – A Multi-layered System;Automatic Detection of Errors in LLM Large Benchmarks Using Frontier Model Consensus;harnessing Pre-trained Language Models for Efficient Move Recognition in Biomedical Abstracts;Automating Automation: Using LLMs to Generate BPMN Workflows for Robotic Process Automation;Subject Matter Expert versus ChatGPT;bridging the Gap: the Sentiment of User Reviews and 5-Star Ratings;from Latent to Engine Manifolds: Analyzing ImageBind’s Multimodal Embedding Space;object Detection and Counting Using Voice Recognition for Real-Time Human-Machine Teaming Tasks;enhancing Smart Home Security: A Robust Voice Authentication Framework Using K-Nearest Neighbors on IoT Dev
In the realm of tool processing, the frequent occurrence of tool tooth fractures poses a significant challenge, necessitating precise localization, detection, and identification of damaged teeth for high-precision saw...
详细信息
the proceedings contain 35 papers. the topics discussed include: investigation of fundamental algorithms for cooperative exploration of mobile agents in search and rescue scenarios;self-explanation as a basis for self...
ISBN:
(纸本)9798350337464
the proceedings contain 35 papers. the topics discussed include: investigation of fundamental algorithms for cooperative exploration of mobile agents in search and rescue scenarios;self-explanation as a basis for self-integration – the autonomous passenger ferry scenario;modelling adaptive autonomic cloud application utility using template functions;local estimation vs global information: the benefits of slower timescales;engage–envision–enact: self-organized governance for self-improving socio-technical systems;interoperable AI for self-organization;disjoint lookups in Kademlia for random ids;infrastructures for the edge-cloud continuum on a small scale: a practical case study;semi-automatic integration of little languages;and exploring the potential of self-organizing applications in energy networks.
Ultra-Dense Networks (UDNs) represent a promising paradigm for meeting the ever-increasing demand for high data rates and connectivity in modern wireless communication systems. this paper investigates the interplay of...
详细信息
the proceedings contain 18 papers. the topics discussed include: a new distributed optimization algorithm for MINLPs with affinely coupled decision variables;ranking fuzzy numbers by similarity measure index;compresse...
ISBN:
(纸本)9781450377324
the proceedings contain 18 papers. the topics discussed include: a new distributed optimization algorithm for MINLPs with affinely coupled decision variables;ranking fuzzy numbers by similarity measure index;compressed construction work schedule: modeling of man-hour estimation of engineering activities for housing projects;optimization of stochastic computing based deep learning systems with parallel finite state machine implementation;a hybrid CNN Swarm-transfer learning approach for fault classification;comparative study of features selection methods: case of denial of service attacks forecasting;on malware detection in the android operating system;and evaluation of approaches for designing and developing decentralized applications on blockchain.
暂无评论