We propose Multiplier-less INTeger (MINT) quantization, a uniform quantization scheme that efficiently compresses weights and membrane potentials in spiking neural networks (SNNs). Unlike previous SNN quantization methods, MINT quantizes memory-intensive membrane potentials to an extremely low precision (2-bit), significantly reducing the memory footprint. MINT also shares the quantization scaling factor between weights and membrane potentials, eliminating the need for multipliers required in conventional uniform quantization. Experimental results show that our method matches the accuracy of full-precision models and other state-of-the-art SNN quantization techniques while surpassing them in memory footprint reduction and hardware cost efficiency at deployment. For example, 2-bit MINT VGG-16 achieves 90.6% accuracy on CIFAR-10, with roughly 93.8% reduction in memory footprint from the full-precision model and 90% reduction in computation energy compared to vanilla uniform quantization at deployment. The code is available at //github.com/Intelligent-Computing-Lab-Yale/MINT-Quantization.
相關內容
In the realm of edge computing, the increasing demand for high Quality of Service (QoS), particularly in dynamic multimedia streaming applications (e.g., Augmented Reality/Virtual Reality and online gaming), has prompted the need for effective solutions. Nevertheless, adopting an edge paradigm grounded in distributed computing has exacerbated the issue of tail latency. Given a limited variety of multimedia services supported by edge servers and the dynamic nature of user requests, employing traditional queuing methods to model tail latency in distributed edge computing is challenging, substantially exacerbating head-of-line (HoL) blocking. In response to this challenge, we have developed a learning-based scheduling method to mitigate the overall tail latency, which adaptively selects appropriate edge servers for execution as incoming distributed tasks vary with unknown size. To optimize the utilization of the edge computing paradigm, we leverage Laplace transform techniques to theoretically derive an upper bound for the response time of edge servers. Subsequently, we integrate this upper bound into reinforcement learning to facilitate tail learning and enable informed decisions for autonomous distributed scheduling. The experiment results demonstrate the efficiency in reducing tail latency compared to existing methods.
Reconfigurable intelligent surfaces (RISs) are rapidly gaining prominence in the realm of fifth generation (5G)-Advanced, and predominantly, sixth generation (6G) mobile networks, offering a revolutionary approach to optimizing wireless communications. This article delves into the intricate world of the RIS technology, exploring its diverse hardware architectures and the resulting versatile operating modes. These include RISs with signal reception and processing units, sensors, amplification units, transmissive capability, multiple stacked components, and dynamic metasurface antennas. Furthermore, we shed light on emerging RIS applications, such as index and reflection modulation, non-coherent modulation, next generation multiple access, integrated sensing and communications (ISAC), energy harvesting, as well as aerial and vehicular networks. These exciting applications are set to transform the way we will wirelessly connect in the upcoming era of 6G. Finally, we review recent experimental RIS setups and present various open problems of the overviewed RIS hardware architectures and their applications. From enhancing network coverage to enabling new communication paradigms, RIS-empowered connectivity is poised to play a pivotal role in shaping the future of wireless networking. This article unveils the underlying principles and potential impacts of RISs, focusing on cutting-edge developments of this physical-layer smart connectivity technology.
Background: Rim+ lesions in multiple sclerosis (MS), detectable via Quantitative Susceptibility Mapping (QSM), correlate with increased disability. Existing literature lacks quantitative analysis of these lesions. We introduce RimSet for quantitative identification and characterization of rim+ lesions on QSM. Methods: RimSet combines RimSeg, an unsupervised segmentation method using level-set methodology, and radiomic measurements with Local Binary Pattern texture descriptors. We validated RimSet using simulated QSM images and an in vivo dataset of 172 MS subjects with 177 rim+ and 3986 rim-lesions. Results: RimSeg achieved a 78.7% Dice score against the ground truth, with challenges in partial rim lesions. RimSet detected rim+ lesions with a partial ROC AUC of 0.808 and PR AUC of 0.737, surpassing existing methods. QSMRim-Net showed the lowest mean square error (0.85) and high correlation (0.91; 95% CI: 0.88, 0.93) with expert annotations at the subject level.
Large Language Models (LLMs) exhibit a unique phenomenon known as emergent abilities, demonstrating adeptness across numerous tasks, from text summarization to code generation. While these abilities open up novel avenues in software design and crafting, their incorporation presents substantial challenges. Developers face decisions regarding the use of LLMs for directly performing tasks within applications as well as for generating and executing code to accomplish these tasks. Moreover, effective prompt design becomes a critical concern, given the necessity of extracting data from natural language outputs. To address these complexities, this paper introduces AskIt, a domain-specific language (DSL) specifically designed for LLMs. AskIt simplifies LLM integration by providing a unified interface that not only allows for direct task execution using LLMs but also supports the entire cycle of code generation and execution. This dual capability is achieved through (1) type-guided output control, (2) template-based function definitions, and (3) prompt generation for both usage modes. Our evaluations underscore AskIt's effectiveness. Across 50 tasks, AskIt generated concise prompts, achieving a 16.14 % reduction in prompt length compared to benchmarks. Additionally, by enabling a seamless transition between using LLMs directly in applications and for generating code, AskIt achieved significant efficiency improvements, as observed in our GSM8K benchmark experiments. The implementations of AskIt in TypeScript and Python are available at //github.com/katsumiok/ts-askit and //github.com/katsumiok/pyaskit, respectively.
Supplying data augmentation to conversational question answering (CQA) can effectively improve model performance. However, there is less improvement from single-turn datasets in CQA due to the distribution gap between single-turn and multi-turn datasets. On the other hand, while numerous single-turn datasets are available, we have not utilized them effectively. To solve this problem, we propose a novel method to convert single-turn datasets to multi-turn datasets. The proposed method consists of three parts, namely, a QA pair Generator, a QA pair Reassembler, and a question Rewriter. Given a sample consisting of context and single-turn QA pairs, the Generator obtains candidate QA pairs and a knowledge graph based on the context. The Reassembler utilizes the knowledge graph to get sequential QA pairs, and the Rewriter rewrites questions from a conversational perspective to obtain a multi-turn dataset S2M. Our experiments show that our method can synthesize effective training resources for CQA. Notably, S2M ranks 1st place on the QuAC leaderboard at the time of submission (Aug 24th, 2022).
We introduce a new approach for generating sequences of implied volatility (IV) surfaces across multiple assets that is faithful to historical prices. We do so using a combination of functional data analysis and neural stochastic differential equations (SDEs) combined with a probability integral transform penalty to reduce model misspecification. We demonstrate that learning the joint dynamics of IV surfaces and prices produces market scenarios that are consistent with historical features and lie within the sub-manifold of surfaces that are essentially free of static arbitrage. Finally, we demonstrate that delta hedging using the simulated surfaces generates profit and loss (P&L) distributions that are consistent with realised P&Ls.
Multimodal sentiment analysis (MSA) finds extensive applications, but the presence of missing modalities in real-world environments requires researchers to enhance the robustness of models, often demanding significant efforts. Multimodal neural architecture search (MNAS) is a more efficient approach. However, current MNAS methods, while effective in integrating multi-level information, are incapable of simultaneously searching for optimal operations to extract modality-specific information. This weakens the robustness of the model in addressing diverse scenarios. Moreover, these methods also fall short in enhancing the capture of emotional cues. In this paper, we propose robust-sentiment multimodal neural architecture search (RMNAS) framework. Specifically, we utilize the Transformer as a unified architecture for various modalities and incorporate a search for token mixers to enhance the encoding capacity of individual modalities and improve robustness across diverse scenarios. Subsequently, we leverage BM-NAS to integrate multi-level information. Furthermore, we incorporate local sentiment variation trends to guide the token mixers computation, enhancing the model's ability to capture sentiment context. Experimental results demonstrate that our approach outperforms or competitively matches existing state-of-the-art approaches in incomplete multimodal learning, both in sentence-level and dialogue-level MSA tasks, without the need for knowledge of incomplete learning.
Most existing event extraction (EE) methods merely extract event arguments within the sentence scope. However, such sentence-level EE methods struggle to handle soaring amounts of documents from emerging applications, such as finance, legislation, health, etc., where event arguments always scatter across different sentences, and even multiple such event mentions frequently co-exist in the same document. To address these challenges, we propose a novel end-to-end model, Doc2EDAG, which can generate an entity-based directed acyclic graph to fulfill the document-level EE (DEE) effectively. Moreover, we reformalize a DEE task with the no-trigger-words design to ease the document-level event labeling. To demonstrate the effectiveness of Doc2EDAG, we build a large-scale real-world dataset consisting of Chinese financial announcements with the challenges mentioned above. Extensive experiments with comprehensive analyses illustrate the superiority of Doc2EDAG over state-of-the-art methods. Data and codes can be found at //github.com/dolphin-zs/Doc2EDAG.
The problem of Multiple Object Tracking (MOT) consists in following the trajectory of different objects in a sequence, usually a video. In recent years, with the rise of Deep Learning, the algorithms that provide a solution to this problem have benefited from the representational power of deep models. This paper provides a comprehensive survey on works that employ Deep Learning models to solve the task of MOT on single-camera videos. Four main steps in MOT algorithms are identified, and an in-depth review of how Deep Learning was employed in each one of these stages is presented. A complete experimental comparison of the presented works on the three MOTChallenge datasets is also provided, identifying a number of similarities among the top-performing methods and presenting some possible future research directions.
With the capability of modeling bidirectional contexts, denoising autoencoding based pretraining like BERT achieves better performance than pretraining approaches based on autoregressive language modeling. However, relying on corrupting the input with masks, BERT neglects dependency between the masked positions and suffers from a pretrain-finetune discrepancy. In light of these pros and cons, we propose XLNet, a generalized autoregressive pretraining method that (1) enables learning bidirectional contexts by maximizing the expected likelihood over all permutations of the factorization order and (2) overcomes the limitations of BERT thanks to its autoregressive formulation. Furthermore, XLNet integrates ideas from Transformer-XL, the state-of-the-art autoregressive model, into pretraining. Empirically, XLNet outperforms BERT on 20 tasks, often by a large margin, and achieves state-of-the-art results on 18 tasks including question answering, natural language inference, sentiment analysis, and document ranking.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191