用于神经形态计算的生物学启发的尖峰神经元是具有动态状态变量的非线性滤波器 - 与深度学习中使用的无状态神经元模型非常不同。 Notel Intel的神经形态研究处理器Loihi 2的下一个版本支持各种具有完全可编程动态的最有状态尖峰神经元模型。在这里，我们展示了先进的尖峰神经元模型，可用于有效地处理仿真Loihi 2硬件的仿真实验中的流数据。在一个示例中，共振和火（RF）神经元用于计算短时间傅里叶变换（STFT），其具有类似的计算复杂度，但是输出带宽的47倍而不是传统的STFT。在另一个例子中，我们描述了一种使用时间率RF神经元的光学流量估计算法，其需要比传统的基于DNN的解决方案超过90倍。我们还展示了有前途的初步结果，使用BackPropagation培训RF神经元进行音频分类任务。最后，我们表明，跳跃的血管谐振器 - RF神经元的变体 - 重复耳蜗的新特性，并激励一种有效的基于尖峰的谱图编码器。

With the advent of Neural Style Transfer (NST), stylizing an image has become quite popular. A convenient way for extending stylization techniques to videos is by applying them on a per-frame basis. However, such per-frame application usually lacks temporal-consistency expressed by undesirable flickering artifacts. Most of the existing approaches for enforcing temporal-consistency suffers from one or more of the following drawbacks. They (1) are only suitable for a limited range of stylization techniques, (2) can only be applied in an offline fashion requiring the complete video as input, (3) cannot provide consistency for the task of stylization, or (4) do not provide interactive consistency-control. Note that existing consistent video-filtering approaches aim to completely remove flickering artifacts and thus do not respect any specific consistency-control aspect. For stylization tasks, however, consistency-control is an essential requirement where a certain amount of flickering can add to the artistic look and feel. Moreover, making this control interactive is paramount from a usability perspective. To achieve the above requirements, we propose an approach that can stylize video streams while providing interactive consistency-control. Apart from stylization, our approach also supports various other image processing filters. For achieving interactive performance, we develop a lite optical-flow network that operates at 80 Frames per second (FPS) on desktop systems with sufficient accuracy. We show that the final consistent video-output using our flow network is comparable to that being obtained using state-of-the-art optical-flow network. Further, we employ an adaptive combination of local and global consistent features and enable interactive selection between the two. By objective and subjective evaluation, we show that our method is superior to state-of-the-art approaches.

Large language models have ushered in a golden age of semantic parsing. The seq2seq paradigm allows for open-schema and abstractive attribute and relation extraction given only small amounts of finetuning data. Language model pretraining has simultaneously enabled great strides in natural language inference, reasoning about entailment and implication in free text. These advances motivate us to construct ImPaKT, a dataset for open-schema information extraction, consisting of around 2500 text snippets from the C4 corpus, in the shopping domain (product buying guides), professionally annotated with extracted attributes, types, attribute summaries (attribute schema discovery from idiosyncratic text), many-to-one relations between compound and atomic attributes, and implication relations. We release this data in hope that it will be useful in fine tuning semantic parsers for information extraction and knowledge base construction across a variety of domains. We evaluate the power of this approach by fine-tuning the open source UL2 language model on a subset of the dataset, extracting a set of implication relations from a corpus of product buying guides, and conducting human evaluations of the resulting predictions.

Language models have recently achieved strong performance across a wide range of NLP benchmarks. However, unlike benchmarks, real world tasks are often poorly specified, and agents must deduce the user's intended behavior from a combination of context, instructions, and examples. We investigate how both humans and models behave in the face of such task ambiguity by proposing AmbiBench, a new benchmark of six ambiguously-specified classification tasks. We evaluate humans and models on AmbiBench by seeing how well they identify the intended task using 1) instructions with varying degrees of ambiguity, and 2) different numbers of labeled examples. We find that the combination of model scaling (to 175B parameters) and training with human feedback data enables models to approach or exceed the accuracy of human participants across tasks, but that either one alone is not sufficient. In addition, we show how to dramatically improve the accuracy of language models trained without large-scale human feedback training by finetuning on a small number of ambiguous in-context examples, providing a promising direction for teaching models to generalize well in the face of ambiguity.

Fusion-in-Decoder (FiD) is a powerful retrieval-augmented language model that sets the state-of-the-art on many knowledge-intensive NLP tasks. However, FiD suffers from very expensive inference. We show that the majority of inference time results from memory bandwidth constraints in the decoder, and propose two simple changes to the FiD architecture to speed up inference by 7x. The faster decoder inference then allows for a much larger decoder. We denote FiD with the above modifications as FiDO, and show that it strongly improves performance over existing FiD models for a wide range of inference budgets. For example, FiDO-Large-XXL performs faster inference than FiD-Base and achieves better performance than FiD-Large.

Autonomous driving has a natural bi-level structure. The goal of the upper behavioural layer is to provide appropriate lane change, speeding up, and braking decisions to optimize a given driving task. However, this layer can only indirectly influence the driving efficiency through the lower-level trajectory planner, which takes in the behavioural inputs to produce motion commands. Existing sampling-based approaches do not fully exploit the strong coupling between the behavioural and planning layer. On the other hand, end-to-end Reinforcement Learning (RL) can learn a behavioural layer while incorporating feedback from the lower-level planner. However, purely data-driven approaches often fail in safety metrics in unseen environments. This paper presents a novel alternative; a parameterized bi-level optimization that jointly computes the optimal behavioural decisions and the resulting downstream trajectory. Our approach runs in real-time using a custom GPU-accelerated batch optimizer, and a Conditional Variational Autoencoder learnt warm-start strategy. Extensive simulations show that our approach outperforms state-of-the-art model predictive control and RL approaches in terms of collision rate while being competitive in driving efficiency.

Determination of treatment need of posterior capsular opacification (PCO)-- one of the most common complication of cataract surgery -- is a difficult process due to its local unavailability and the fact that treatment is provided only after PCO occurs in the central visual axis. In this paper we propose a deep learning (DL)-based method to first segment PCO images then classify the images into \textit{treatment required} and \textit{not yet required} cases in order to reduce frequent hospital visits. To train the model, we prepare a training image set with ground truths (GT) obtained from two strategies: (i) manual and (ii) automated. So, we have two models: (i) Model 1 (trained with image set containing manual GT) (ii) Model 2 (trained with image set containing automated GT). Both models when evaluated on validation image set gave Dice coefficient value greater than 0.8 and intersection-over-union (IoU) score greater than 0.67 in our experiments. Comparison between gold standard GT and segmented results from our models gave a Dice coefficient value greater than 0.7 and IoU score greater than 0.6 for both the models showing that automated ground truths can also result in generation of an efficient model. Comparison between our classification result and clinical classification shows 0.98 F2-score for outputs from both the models.

Timely and effective response to humanitarian crises requires quick and accurate analysis of large amounts of text data - a process that can highly benefit from expert-assisted NLP systems trained on validated and annotated data in the humanitarian response domain. To enable creation of such NLP systems, we introduce and release HumSet, a novel and rich multilingual dataset of humanitarian response documents annotated by experts in the humanitarian response community. The dataset provides documents in three languages (English, French, Spanish) and covers a variety of humanitarian crises from 2018 to 2021 across the globe. For each document, HUMSET provides selected snippets (entries) as well as assigned classes to each entry annotated using common humanitarian information analysis frameworks. HUMSET also provides novel and challenging entry extraction and multi-label entry classification tasks. In this paper, we take a first step towards approaching these tasks and conduct a set of experiments on Pre-trained Language Models (PLM) to establish strong baselines for future research in this domain. The dataset is available at https://blog.thedeep.io/humset/.

数字双技术被认为是现代工业发展的组成部分。随着技术Internet技术（IoT）技术的快速发展以及自动化趋势的增加，虚拟世界与物理世界之间的整合现在可以实现生产实用的数字双胞胎。但是，数字双胞胎的现有定义是不完整的，有时是模棱两可的。在此，我们进行了历史审查，并分析了数字双胞胎的现代通用观点，以创建其新的扩展定义。我们还审查并讨论了在安全至关重要的机器人技术应用中数字双胞胎中现有的工作。特别是，由于环境挑战，数字双胞胎在工业应用中的使用需要自动和远程操作。但是，环境中的不确定性可能需要对机器人进行仔细监控和快速适应，这些机器人需要防止安全和成本效益。我们展示了一个案例研究，以开发针对安全至关重要的机器人臂应用框架，并提出系统性能以显示其优势，并讨论未来的挑战和范围。

Digital Twin Technology在现代工业发展中起着关键作用。尤其是，随着技术的技术进步（IoT）以及自主权的日益增长的趋势，配备多传感器的机器人技术可以创建实用的数字双胞胎，这在运营，维护和安全的工业应用程序中特别有用。在此，我们演示了一个现实世界中的数字双胞胎，其中包括安全至关重要的机器人应用程序，并带有Franka-Emika-Panda机器人臂。我们开发并展示了一个避免动态障碍物的边缘辅助协作数字双胞胎，这对于在工业物联网中不确定和动态的环境中运行时可以实时适应机器人。