Tootfinder

Fidelitous Augmentation of Human Accelerometric Data for Deep Learning
Tracey K. M. Lee, H. W. Chan, K. H. Leo, Effie Chew, L. Zhao, Saeid Sanei
https://arxiv.org/abs/2404.14211 <…

Fidelitous Augmentation of Human Accelerometric Data for Deep Learning
Time series (TS) data have consistently been in short supply, yet their demand remains high for training systems in prediction, modeling, classification, and various other applications. Synthesis can serve to expand the sample population, yet it is crucial to maintain the statistical characteristics between the synthesized and the original TS : this ensures consistent sampling of data for both training and testing purposes. However the time domain features of the data may not be maintained. Thi…

Information-based rhythmic transcranial magnetic stimulation to accelerate learning during auditory working memory training: a proof-of-concept study https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2024.1355565/full

Frontiers | Information-based rhythmic transcranial magnetic stimulation to accelerate learning during auditory working memory training: a proof-of-concept study
IntroductionRhythmic transcranial magnetic stimulation (rhTMS) has been shown to enhance auditory working memory manipulation, specifically by boosting theta...

Accelerating Resonance Searches via Signature-Oriented Pre-training
Congqiao Li, Antonios Agapitos, Jovin Drews, Javier Duarte, Dawei Fu, Leyun Gao, Raghav Kansal, Gregor Kasieczka, Louis Moureaux, Huilin Qu, Cristina Mantilla Suarez, Qiang Li
https://arxiv.org/abs/2405.12972

If you know any teens nervously starting in a school jazz band, I highly recommend this. These young actors signed up for these roles with no prior music training (one knew recorder iirc, she stands out), their learning is real as are the very clever methods used to accelerate their musicianship, and to prove it, the band did a promo concert tour when the film was released.
Swing Girls (2004) : Internet Archive

Meta announces its next-generation Meta Training and Inference Accelerator chips for AI training, and says MTIA v1 and the new chips are both now in production (Emilia David/The Verge)
https://www.theverge.com/2024/4/10/24125924/meta-mtia-ai-chips…

Meta’s new AI chips run faster than before
Meta’s planned next-generation MTIA chip will train and optimize inference for its ranking and recommendation models — and maybe soon its generative AI models, too.

This https://arxiv.org/abs/2403.12384 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

An Aligning and Training Framework for Multimodal Recommendations
With the development of multimedia applications, multimodal recommendations are playing an essential role, as they can leverage rich contexts beyond user interactions. Existing methods mainly regard multimodal information as an auxiliary, using them to help learn ID features; however, there exist semantic gaps among multimodal content features and ID features, for which directly using multimodal information as an auxiliary would lead to misalignment in representations of users and items. In thi…

Exploring Green AI for Audio Deepfake Detection
Subhajit Saha, Md Sahidullah, Swagatam Das
https://arxiv.org/abs/2403.14290 https://a…

Exploring Green AI for Audio Deepfake Detection
The state-of-the-art audio deepfake detectors leveraging deep neural networks exhibit impressive recognition performance. Nonetheless, this advantage is accompanied by a significant carbon footprint. This is mainly due to the use of high-performance computing with accelerators and high training time. Studies show that average deep NLP model produces around 626k lbs of CO\textsubscript{2} which is equivalent to five times of average US car emission at its lifetime. This is certainly a massive th…

Accelerating Handover in Mobile Satellite Network
Jiasheng Wu, Shaojie Su, Xiong Wang, Jingjing Zhang, Yue Gao
https://arxiv.org/abs/2403.11502 https://

Accelerating Handover in Mobile Satellite Network
The construction of Low Earth Orbit (LEO) satellite constellations has recently spurred tremendous attention from academia and industry. 5G and 6G standards have specified LEO satellite network as a key component of 5G and 6G networks. However, ground terminals experience frequent, high-latency handover incurred by satellites' fast travelling speed, which deteriorates the performance of latency-sensitive applications. To address this challenge, we propose a novel handover flowchart for mobile s…

An Aligning and Training Framework for Multimodal Recommendations
Yifan Liu, Kangning Zhang, Xiangyuan Ren, Yanhua Huang, Jiarui Jin, Yingjie Qin, Ruilong Su, Ruiwen Xu, Weinan Zhang
https://arxiv.org/abs/2403.12384

An Aligning and Training Framework for Multimodal Recommendations
With the development of multimedia applications, multimodal recommendations are playing an essential role, as they can leverage rich contexts beyond user interactions. Existing methods mainly regard multimodal information as an auxiliary, using them to help learn ID features; however, there exist semantic gaps among multimodal content features and ID features, for which directly using multimodal information as an auxiliary would lead to misalignment in representations of users and items. In thi…

Intel debuts its Gaudi 3 AI chips, set for Q3 mass production, saying they offer up to 1.7x the training performance and 40% better efficiency than Nvidia H100s (Paul Alcorn/Tom's Hardware)
https://www.t…

Intel details Guadi 3 at Vision 2024 — new AI accelerator sampling to partners now, volume production in Q3
Intel announced its new Gaudi 3 AI processors at its Vision 2024 event, claiming they offer up to 1.7X the training performance, 50% better inference, and 40% better efficiency than Nvidia’s market-leading H100 processors, but for significantly less money.