English
Related papers

Related papers: New Directions in International Masterclasses

200 papers

Deep learning training involves a large number of operations, which are dominated by high dimensionality Matrix-Vector Multiplies (MVMs). This has motivated hardware accelerators to enhance compute efficiency, but where data movement and…

Systems and Control · Electrical Eng. & Systems 2022-07-07 Christopher Grimm , Naveen Verma

Machine learning continues to grow in popularity in academia, in industry, and is increasingly used in other fields. However, most of the common metrics used to evaluate even simple binary classification models have shortcomings that are…

Machine Learning · Computer Science 2024-12-25 David H. Brown , Davide Chicco

Deep neural networks have shown remarkable performance when trained on independent and identically distributed data from a fixed set of classes. However, in real-world scenarios, it can be desirable to train models on a continuous stream of…

Machine Learning · Computer Science 2023-09-04 Nicolas Michel , Giovanni Chierchia , Romain Negrel , Jean-François Bercher , Toshihiko Yamasaki

International Linear Collider (ILC) is an electron-positron collider with the initial center-of-mass energy of 500 GeV which is upgradable to about 1 TeV later on. Its goal is to study the physics at TeV scale with unprecedented high…

High Energy Physics - Phenomenology · Physics 2008-11-26 Hitoshi Yamamoto

Extracting actionable information rapidly from data produced by instruments such as the Linac Coherent Light Source (LCLS-II) and Advanced Photon Source Upgrade (APS-U) is becoming ever more challenging due to high (up to TB/s) data rates.…

In recent years, deep neural networks have achieved remarkable accuracy in computer vision tasks. With inference time being a crucial factor, particularly in dense prediction tasks such as semantic segmentation, knowledge distillation has…

Computer Vision and Pattern Recognition · Computer Science 2023-08-09 Amir M. Mansourian , Rozhan Ahmadi , Shohreh Kasaei

Double beta decay is indispensable to solve the question of the neutrino mass matrix together with neutrino oscillation experiments. The most sensitive experiment since eight years - the Heidelberg-Moscow experiment in Gran-Sasso - already…

High Energy Physics - Phenomenology · Physics 2016-11-23 H. V. Klapdor-Kleingrothaus

Standard deep learning-based classification approaches require collecting all samples from all classes in advance and are trained offline. This paradigm may not be practical in real-world clinical applications, where new classes are…

Computer Vision and Pattern Recognition · Computer Science 2022-07-05 Sana Ayromlou , Purang Abolmaesumi , Teresa Tsang , Xiaoxiao Li

In this work, we present a novel, machine-learning approach for constructing Multiclass Interpretable Scoring Systems (MISS) - a fully data-driven methodology for generating single, sparse, and user-friendly scoring systems for multiclass…

Machine Learning · Computer Science 2024-01-11 Michal K. Grzeszczyk , Tomasz Trzciński , Arkadiusz Sitek

Incremental Learning (IL) is useful when artificial systems need to deal with streams of data and do not have access to all data at all times. The most challenging setting requires a constant complexity of the deep model and an incremental…

Computer Vision and Pattern Recognition · Computer Science 2020-09-01 Eden Belouadah , Adrian Popescu , Ioannis Kanellos

International Classification of Diseases (ICD) are the de facto codes used globally for clinical coding. These codes enable healthcare providers to claim reimbursement and facilitate efficient storage and retrieval of diagnostic…

Computation and Language · Computer Science 2022-02-22 Pavithra Rajendran , Alexandros Zenonos , Josh Spear , Rebecca Pope

Incremental learning suffers from two challenging problems; forgetting of old knowledge and intransigence on learning new knowledge. Prediction by the model incrementally learned with a subset of the dataset are thus uncertain and the…

Machine Learning · Computer Science 2019-02-05 Dahyun Kim , Jihwan Bae , Yeonsik Jo , Jonghyun Choi

During the past decade, long-baseline neutrino experiments played a fundamental role in confirming neutrino flavor change and in measuring the neutrino mixing matrix with high precision. This role will be amplified with the next generation…

High Energy Physics - Experiment · Physics 2011-03-08 Alexandre Sousa

In-context Learning (ICL) has achieved notable success in the applications of large language models (LLMs). By adding only a few input-output pairs that demonstrate a new task, the LLM can efficiently learn the task during inference without…

Software Engineering · Computer Science 2024-09-10 Zeming Wei , Yihao Zhang , Meng Sun

Traditional binary hard labels for sound event detection (SED) lack details about the complexity and variability of sound event distributions. Recently, a novel annotation workflow is proposed to generate fine-grained non-binary soft…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-08 Han Yin , Jisheng Bai , Mou Wang , Dongyuan Shi , Woon-Seng Gan , Jianfeng Chen

The conclusions of the Physics Working Group of the international scoping study of a future Neutrino Factory and super-beam facility (the ISS) are presented. The ISS was carried by the international community between NuFact05, (the 7th…

High Energy Physics - Phenomenology · Physics 2012-08-27 The ISS Physics Working Group

Human activity recognition, facilitated by smart devices, has recently garnered significant attention. Deep learning algorithms have become pivotal in daily activities, sports, and healthcare. Nevertheless, addressing the challenge of…

Human-Computer Interaction · Computer Science 2024-11-19 Nazanin Sedaghati , Masoud Kargar , Sina Abbaskhani

The international Muon Ionization Cooling Experiment (MICE) will perform a systematic investigation of ionization cooling of a muon beam. The demonstration is based on a simplified version of a neutrino factory cooling channel. As the…

Accelerator Physics · Physics 2019-08-13 M. Bonesini