paper-with-me

Papers Physical Intuition

“Physical Intuition” 태그가 달린 논문 51편 · 필터 해제

Towards understanding how attention mechanism works in deep learning

2024-12-24 · Tianyu Ruan, Shihua Zhang

Attention mechanism has been extensively integrated within mainstream neural network architectures, such as Transformers and graph attention networks. Yet, its underlying working principles remain somewhat elusive. What …

Deep LearningGraph AttentionMetric LearningPhysical Intuition

A Note on Spectral Map

2024-12-05 · Tuğçe Gökdemir, Jakub Rydzewski

In molecular dynamics (MD) simulations, transitions between states are often rare events due to energy barriers that exceed the thermal temperature. Because of their infrequent occurrence and the huge number of degrees o…

Physical Intuition

Automated design of nonreciprocal thermal emitters via Bayesian optimization

2024-09-13 · Bach Do, Sina Jafari Ghalekohneh, Taiwo Adebiyi, Bo Zhao 외

Nonreciprocal thermal emitters that break Kirchhoff's law of thermal radiation promise exciting applications for thermal and energy applications. The design of the bandwidth and angular range of the nonreciprocal effect,…

Bayesian OptimizationPhysical Intuition

InvDesFlow: An AI-driven materials inverse design workflow to explore possible high-temperature superconductors

2024-09-12 · Xiao-Qi Han, Zhenfeng Ouyang, Peng-Jie Guo, Hao Sun 외

The discovery of new superconducting materials, particularly those exhibiting high critical temperature ($T_c$), has been a vibrant area of study within the field of condensed matter physics. Conventional approaches prim…

Physical Intuition

Optimizing Cycle Life Prediction of Lithium-ion Batteries via a Physics-Informed Model

2024-04-26 · Constantin-Daniel Nicolae, Sara Sameer, Nathan Sun, Karena Yan

Accurately measuring the cycle lifetime of commercial lithium-ion batteries is crucial for performance and technology development. We introduce a novel hybrid approach combining a physics-based equation with a self-atten…

Physical Intuition

MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge

2023-11-14 · Bo Ni, Markus J. Buehler

Solving mechanics problems using numerical methods requires comprehensive intelligent capability of retrieving relevant knowledge and theory, constructing and executing codes, analyzing the results, a task that has thus …

Language ModelingLanguage ModellingLarge Language ModelPhysical Intuition

Physics-tailored machine learning reveals unexpected physics in dusty plasmas

2023-10-08 · Wentao Yu, Eslam Abdelaleem, Ilya Nemenman, Justin C. Burton

Dusty plasma is a mixture of ions, electrons, and macroscopic charged particles that is commonly found in space and planetary environments. The particles interact through Coulomb forces mediated by the surrounding plasma…

Physical Intuitionscientific discovery

Constructing Custom Thermodynamics Using Deep Learning

2023-08-08 · Xiaoli Chen, Beatrice W. Soh, Zi-En Ooi, Eleonore Vissol-Gaudin 외

One of the most exciting applications of artificial intelligence (AI) is automated scientific discovery based on previously amassed data, coupled with restrictions provided by known physical principles, including symmetr…

Deep LearningPhysical Intuitionscientific discovery

Generalizing Adam to Manifolds for Efficiently Training Transformers

2023-05-26 · Benedikt Brantner

One of the primary reasons behind the success of neural networks has been the emergence of an array of new, highly-successful optimizers, perhaps most importantly the Adam optimizer. It is widely used for training neural…

Physical Intuition

Bayesian Active Learning for Scanning Probe Microscopy: from Gaussian Processes to Hypothesis Learning

2022-05-30 · Maxim Ziatdinov, Yongtao Liu, Kyle Kelley, Rama Vasudevan 외

Recent progress in machine learning methods, and the emerging availability of programmable interfaces for scanning probe microscopes (SPMs), have propelled automated and autonomous microscopies to the forefront of attent…

Active LearningBayesian InferenceBIG-bench Machine LearningGaussian Processes+1

Training Compute-Optimal Large Language Models

2022-03-29 · Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya 외

We investigate the optimal model size and number of tokens for training a transformer language model under a given compute budget. We find that current large language models are significantly undertrained, a consequence …

AnachronismsAnalogical SimilarityAnalytic EntailmentCausal Judgment+69

Wind Park Power Prediction: Attention-Based Graph Networks and Deep Learning to Capture Wake Losses

2022-01-10 · Lars Ødegaard Bentsen, Narada Dilp Warakagoda, Roy Stenbro, Paal Engelstad

With the increased penetration of wind energy into the power grid, it has become increasingly important to be able to predict the expected power production for larger wind farms. Deep learning (DL) models can learn compl…

Graph AttentionPhysical Intuition

Analytical Modelling of Exoplanet Transit Specroscopy with Dimensional Analysis and Symbolic Regression

2021-12-22 · Konstantin T. Matchev, Katia Matcheva, Alexander Roman

The physical characteristics and atmospheric chemical composition of newly discovered exoplanets are often inferred from their transit spectra which are obtained from complex numerical models of radiative transfer. Alter…

Physical IntuitionregressionSymbolic Regression

Scaling Language Models: Methods, Analysis & Insights from Training Gopher

2021-12-08 · NA 2021 12 · Jack W. Rae, Sebastian Borgeaud, Trevor Cai, Katie Millican 외

Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis o…

Abstract AlgebraAnachronismsAnalogical SimilarityAnalytic Entailment+143

Convolutional Neural Networks Demystified: A Matched Filtering Perspective Based Tutorial

2021-08-26 · Ljubisa Stankovic, Danilo Mandic

Deep Neural Networks (DNN) and especially Convolutional Neural Networks (CNN) are a de-facto standard for the analysis of large volumes of signals and images. Yet, their development and underlying principles have been la…

Dimensionality ReductionPhysical Intuition

Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery

2021-05-03 · ICCV 2021 10 · Samir Yitzhak Gadre, Kiana Ehsani, Shuran Song

People often use physical intuition when manipulating articulated objects, irrespective of object semantics. Motivated by this observation, we identify an important embodied task where an agent must play with objects to …

Motion SegmentationPhysical Intuition

Why is AI hard and Physics simple?

2021-03-31 · Daniel A. Roberts

We discuss why AI is hard and why physics is simple. We discuss how physical intuition and the approach of theoretical physics can be brought to bear on the field of artificial intelligence and specifically machine learn…

BIG-bench Machine LearningLearning TheoryPhysical Intuition

Automated Optical Multi-layer Design via Deep Reinforcement Learning

2020-06-21 · Haozhu Wang, Zeyu Zheng, Chengang Ji, L. Jay Guo

Optical multi-layer thin films are widely used in optical and energy applications requiring photonic designs. Engineers often design such structures based on their physical intuition. However, solely relying on human exp…

Deep Reinforcement LearningPhysical Intuitionreinforcement-learningReinforcement Learning+2

Leveraging 2D Data to Learn Textured 3D Mesh Generation

2020-04-08 · CVPR 2020 6 · Paul Henderson, Vagia Tsiminaki, Christoph H. Lampert

Numerous methods have been proposed for probabilistic generative modelling of 3D objects. However, none of these is able to produce textured objects, which renders them of limited use for practical tasks. In this work, w…

Physical Intuition

Advances in Bayesian Probabilistic Modeling for Industrial Applications

2020-03-26 · Sayan Ghosh, Piyush Pandita, Steven Atkinson, Waad Subber 외

Industrial applications frequently pose a notorious challenge for state-of-the-art methods in the contexts of optimization, designing experiments and modeling unknown physical response. This problem is aggravated by limi…

Physical Intuition
← 이전 21–40 / 51 다음 →