Compared to traditional Artificial Neural Network (ANN), Spiking Neural
Network (SNN) has garnered widespread academic interest for its intrinsic
ability to transmit information in a more biological-inspired and
energy-efficient manner. However, despite previous efforts to optimize the
learning gradients and model structure of SNNs through various methods, SNNs
still lag behind ANNs in terms of performance to some extent. The recently
proposed multi-threshold model provides more possibilities for further
enhancing the learning capability of SNNs. In this paper, we rigorously analyze
the relationship among the multi-threshold model, vanilla spiking model and
quantized ANNs from a mathematical perspective, then propose a novel LM-HT
model, which is an equidistant multi-hierarchical model that can dynamically
regulate the global input current and membrane potential leakage on the time
dimension. In addition, we note that the direct training algorithm based on the
LM-HT model can seamlessly integrate with the traditional ANN-SNN Conversion
framework. This novel hybrid learning framework can effectively improve the
relatively poor performance of converted SNNs under low time latency. Extensive
experimental results have demonstrated that our LM-HT model can significantly
outperform previous state-of-the-art works on various types of datasets, which
promote SNNs to achieve a brand-new level of performance comparable to
quantized ANNs.

通过分析多阈值模型、简单尖峰模型和量化人工神经网络之间的关系，从数学角度提出了一种新颖的 LM-HT 模型，该模型是一个等距多层次模型，可以在时间维度上动态调节全局输入电流和膜电位漏电。我们注意到基于 LM-HT 模型的直接训练算法可以与传统的 ANN-SNN 转化框架无缝集成，该新颖的混合学习框架可以有效提高低时间延迟下经过转换的 SNN 的性能。大量的实验证明，我们的 LM-HT 模型在各类数据集上明显优于之前的最先进工作，促使 SNNs 达到了与量化 ANNs 相当的全新水平的性能。

LM-HT SNN：通过可学习的多层次阈值模型增强 SNN 至 ANN 的性能

LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through  Learnable Multi-hierarchical Threshold Model

Leveraging large language models (LLMs) to integrate off-the-shelf tools
(e.g., visual models and image processing functions) is a promising research
direction to build powerful visual assistants for solving diverse visual tasks.
However, the learning capability is rarely explored in existing methods, as
they freeze the used tools after deployment, thereby limiting the
generalization to new environments requiring specific knowledge. In this paper,
we propose CLOVA, a Closed-LOop Visual Assistant to address this limitation,
which encompasses inference, reflection, and learning phases in a closed-loop
framework. During inference, LLMs generate programs and execute corresponding
tools to accomplish given tasks. The reflection phase introduces a multimodal
global-local reflection scheme to analyze whether and which tool needs to be
updated based on environmental feedback. Lastly, the learning phase uses three
flexible manners to collect training data in real-time and introduces a novel
prompt tuning scheme to update the tools, enabling CLOVA to efficiently learn
specific knowledge for new environments without human involvement. Experiments
show that CLOVA outperforms tool-usage methods by 5% in visual question
answering and multiple-image reasoning tasks, by 10% in knowledge tagging
tasks, and by 20% in image editing tasks, highlighting the significance of the
learning capability for general visual assistants.

本文介绍了一种闭环视觉助手 CLOVA，利用大型语言模型（LLMs）将现成工具集成在一起，通过推理、反馈和学习三个阶段来解决视觉助手在新环境中推广使用的能力有限的问题。实验结果显示，CLOVA 在视觉问题回答、知识标注和图像编辑任务方面的性能均超过其他方法。

CLOVA：带有工具使用和更新的封闭循环视觉助手

CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update

Among various soft computing approaches for time series forecasting, Fuzzy
Cognitive Maps (FCM) have shown remarkable results as a tool to model and
analyze the dynamics of complex systems. FCM have similarities to recurrent
neural networks and can be classified as a neuro-fuzzy method. In other words,
FCMs are a mixture of fuzzy logic, neural network, and expert system aspects,
which act as a powerful tool for simulating and studying the dynamic behavior
of complex systems. The most interesting features are knowledge
interpretability, dynamic characteristics and learning capability. The goal of
this survey paper is mainly to present an overview on the most relevant and
recent FCM-based time series forecasting models proposed in the literature. In
addition, this article considers an introduction on the fundamentals of FCM
model and learning methodologies. Also, this survey provides some ideas for
future research to enhance the capabilities of FCM in order to cover some
challenges in the real-world experiments such as handling non-stationary data
and scalability issues. Moreover, equipping FCMs with fast learning algorithms
is one of the major concerns in this area.

该论文主要介绍了 Fuzzy Cognitive Maps 在时间序列预测中的应用。该方法具有知识可解释性、动态特性和学习能力。该论文综述了文献中最重要和最新的基于 FCM 的时间序列预测模型，并提出了应对现实实验中的挑战和未来研究的思路，如处理非平稳数据和可扩展性问题。此外，为了使其具备快速学习算法，将 FCMs 与这一领域的主要关注点之一。