المؤلفون: Yuan, Kai, Dong, Xinxin, Xu, Liyang, Xia, Ming, Zhang, Jianguo

المصدر: 2024 Conference of Science and Technology for Integrated Circuits (CSTIC) Science and Technology for Integrated Circuits (CSTIC), 2024 Conference of. :1-06 Mar, 2024

Relation: 2024 Conference of Science and Technology for Integrated Circuits (CSTIC)

المؤلفون: Liu, Zuxin, Hoang, Thai, Zhang, Jianguo, Zhu, Ming, Lan, Tian, Kokane, Shirley, Tan, Juntao, Yao, Weiran, Liu, Zhiwei, Feng, Yihao, Murthy, Rithesh, Yang, Liangwei, Savarese, Silvio, Niebles, Juan Carlos, Wang, Huan, Heinecke, Shelby, Xiong, Caiming

مصطلحات موضوعية: Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Software Engineering

الوصف: The advancement of function-calling agent models requires diverse, reliable, and high-quality datasets. This paper presents APIGen, an automated data generation pipeline designed to synthesize verifiable high-quality datasets for function-calling applications. We leverage APIGen and collect 3,673 executable APIs across 21 different categories to generate diverse function-calling datasets in a scalable and structured manner. Each data in our dataset is verified through three hierarchical stages: format checking, actual function executions, and semantic verification, ensuring its reliability and correctness. We demonstrate that models trained with our curated datasets, even with only 7B parameters, can achieve state-of-the-art performance on the Berkeley Function-Calling Benchmark, outperforming multiple GPT-4 models. Moreover, our 1B model achieves exceptional performance, surpassing GPT-3.5-Turbo and Claude-3 Haiku. We release a dataset containing 60,000 high-quality entries, aiming to advance the field of function-calling agent domains. The dataset is available on Huggingface: https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k and the project homepage: https://apigen-pipeline.github.io/

URL الوصول: http://arxiv.org/abs/2406.18518

المؤلفون: Shen, Shuaijie, Zhang, Rui, Wang, Chao, Huang, Renzhuo, Tuerhong, Aiersi, Guo, Qinghai, Lu, Zhichao, Zhang, Jianguo, Leng, Luziwei

المصدر: J Membr Comput (2024)

مصطلحات موضوعية: Computer Science - Neural and Evolutionary Computing

الوصف: Spiking neural networks (SNNs) are gaining increasing attention as potential computationally efficient alternatives to traditional artificial neural networks(ANNs). However, the unique information propagation mechanisms and the complexity of SNN neuron models pose challenges for adopting traditional methods developed for ANNs to SNNs. These challenges include both weight learning and architecture design. While surrogate gradient learning has shown some success in addressing the former challenge, the latter remains relatively unexplored. Recently, a novel paradigm utilizing evolutionary computation methods has emerged to tackle these challenges. This approach has resulted in the development of a variety of energy-efficient and high-performance SNNs across a wide range of machine learning benchmarks. In this paper, we present a survey of these works and initiate discussions on potential challenges ahead.

URL الوصول: http://arxiv.org/abs/2406.12552

المؤلفون: Murthy, Rithesh, Yang, Liangwei, Tan, Juntao, Awalgaonkar, Tulika Manoj, Zhou, Yilun, Heinecke, Shelby, Desai, Sachin, Wu, Jason, Xu, Ran, Tan, Sarah, Zhang, Jianguo, Liu, Zhiwei, Kokane, Shirley, Liu, Zuxin, Zhu, Ming, Wang, Huan, Xiong, Caiming, Savarese, Silvio

مصطلحات موضوعية: Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning

الوصف: The deployment of Large Language Models (LLMs) and Large Multimodal Models (LMMs) on mobile devices has gained significant attention due to the benefits of enhanced privacy, stability, and personalization. However, the hardware constraints of mobile devices necessitate the use of models with fewer parameters and model compression techniques like quantization. Currently, there is limited understanding of quantization's impact on various task performances, including LLM tasks, LMM tasks, and, critically, trust and safety. There is a lack of adequate tools for systematically testing these models on mobile devices. To address these gaps, we introduce MobileAIBench, a comprehensive benchmarking framework for evaluating mobile-optimized LLMs and LMMs. MobileAIBench assesses models across different sizes, quantization levels, and tasks, measuring latency and resource consumption on real devices. Our two-part open-source framework includes a library for running evaluations on desktops and an iOS app for on-device latency and hardware utilization measurements. Our thorough analysis aims to accelerate mobile AI research and deployment by providing insights into the performance and feasibility of deploying LLMs and LMMs on mobile platforms.

URL الوصول: http://arxiv.org/abs/2406.10290

المؤلفون: Li, Yizhuo, Zhang, Jianguo, Hu, Fengling, Chen, Peng, Zhang, Han

المصدر: 2023 8th International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS) Intelligent Informatics and Biomedical Sciences (ICIIBMS), 2023 8th International Conference on. 8:37-41 Nov, 2023

Relation: 2023 8th International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)

المؤلفون: Zhang, Jianguo, Zhang, Han, Song, Liang, Li, Yizhuo, Chen, Peng

المصدر: 2023 8th International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS) Intelligent Informatics and Biomedical Sciences (ICIIBMS), 2023 8th International Conference on. 8:242-247 Nov, 2023

Relation: 2023 8th International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS)

المؤلفون: Chen, Kanghao, Lin, Sijia, Zhang, Jianguo, Zheng, Wei-Shi, Wang, Ruixuan

المصدر: 2023 China Automation Congress (CAC) Automation Congress (CAC), 2023 China. :8805-8811 Nov, 2023

Relation: 2023 China Automation Congress (CAC)

المؤلفون: Zhang, Yipeng, Liu, Lawrence, Ding, Yuanyi, Chen, Xin, Monsoor, Tonmoy, Daida, Atsuro, Oana, Shingo, Hussain, Shaun, Sankar, Raman, Fallah, Aria, Santana-Gomez, Cesar, Speier, William, Zhang, Jianguo, Nariai, Hiroki, Staba, Richard, Engel, Jerome, Roychowdhury, Vwani

المصدر: Journal of Neural Engineering. 21(3)

مصطلحات موضوعية: convolutional neural networks, high-frequency oscillations, neurophysiology, Deep Learning, Electroencephalography, Animals, Rats, Algorithms, Epilepsy, Software, Humans, Hippocampus

الوصف: Objective. This study aims to develop and validate an end-to-end software platform, PyHFO, that streamlines the application of deep learning (DL) methodologies in detecting neurophysiological biomarkers for epileptogenic zones from EEG recordings.Approach. We introduced PyHFO, which enables time-efficient high-frequency oscillation (HFO) detection algorithms like short-term energy and Montreal Neurological Institute and Hospital detectors. It incorporates DL models for artifact and HFO with spike classification, designed to operate efficiently on standard computer hardware.Main results. The validation of PyHFO was conducted on three separate datasets: the first comprised solely of grid/strip electrodes, the second a combination of grid/strip and depth electrodes, and the third derived from rodent studies, which sampled the neocortex and hippocampus using depth electrodes. PyHFO demonstrated an ability to handle datasets efficiently, with optimization techniques enabling it to achieve speeds up to 50 times faster than traditional HFO detection applications. Users have the flexibility to employ our pre-trained DL model or use their EEG data for custom model training.Significance. PyHFO successfully bridges the computational challenge faced in applying DL techniques to EEG data analysis in epilepsy studies, presenting a feasible solution for both clinical and research settings. By offering a user-friendly and computationally efficient platform, PyHFO paves the way for broader adoption of advanced EEG data analysis tools in clinical practice and fosters potential for large-scale research collaborations.

وصف الملف: application/pdf

URL الوصول: https://escholarship.org/uc/item/11n5m5w0
https://escholarship.org/content/qt11n5m5w0/qt11n5m5w0.pdf

المؤلفون: Yin, Zixiao, Yu, Huiling, Yuan, Tianshuo, Smyth, Clay, Anjum, Md, Zhu, Guanyu, Ma, Ruoyu, Xu, Yichen, An, Qi, Gan, Yifei, Merk, Timon, Qin, Guofan, Xie, Hutao, Zhang, Ning, Wang, Chunxue, Jiang, Yin, Meng, Fangang, Yang, Anchao, Neumann, Wolf-Julian, Li, Luming, Zhang, Jianguo, Starr, Philip, Little, Simon

المصدر: npj Digital Medicine. 7(1)

الوصف: Sleep disturbances profoundly affect the quality of life in individuals with neurological disorders. Closed-loop deep brain stimulation (DBS) holds promise for alleviating sleep symptoms, however, this technique necessitates automated sleep stage decoding from intracranial signals. We leveraged overnight data from 121 patients with movement disorders (Parkinsons disease, Essential Tremor, Dystonia, Essential Tremor, Huntingtons disease, and Tourettes syndrome) in whom synchronized polysomnograms and basal ganglia local field potentials were recorded, to develop a generalized, multi-class, sleep specific decoder - BGOOSE. This generalized model achieved 85% average accuracy across patients and across disease conditions, even in the presence of recordings from different basal ganglia targets. Furthermore, we also investigated the role of electrocorticography on decoding performances and proposed an optimal decoding map, which was shown to facilitate channel selection for optimal model performances. BGOOSE emerges as a powerful tool for generalized sleep decoding, offering exciting potentials for the precision stimulation delivery of DBS and better management of sleep disturbances in movement disorders.

وصف الملف: application/pdf

URL الوصول: https://escholarship.org/uc/item/9vg09337

المؤلفون: Wang, Hao, Luo, Shengda, Hu, Guosheng, Zhang, Jianguo

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Multimedia

الوصف: Multimodal learning with incomplete input data (missing modality) is practical and challenging. In this work, we conduct an in-depth analysis of this challenge and find that modality dominance has a significant negative impact on the model training, greatly degrading the missing modality performance. Motivated by Grad-CAM, we introduce a novel indicator, gradients, to monitor and reduce modality dominance which widely exists in the missing-modality scenario. In aid of this indicator, we present a novel Gradient-guided Modality Decoupling (GMD) method to decouple the dependency on dominating modalities. Specifically, GMD removes the conflicted gradient components from different modalities to achieve this decoupling, significantly improving the performance. In addition, to flexibly handle modal-incomplete data, we design a parameter-efficient Dynamic Sharing (DS) framework which can adaptively switch on/off the network parameters based on whether one modality is available. We conduct extensive experiments on three popular multimodal benchmarks, including BraTS 2018 for medical segmentation, CMU-MOSI, and CMU-MOSEI for sentiment analysis. The results show that our method can significantly outperform the competitors, showing the effectiveness of the proposed solutions. Our code is released here: https://github.com/HaoWang420/Gradient-guided-Modality-Decoupling.
Comment: AAAI24

URL الوصول: http://arxiv.org/abs/2402.16318