This paper presents a Neuromorphic Starter Kit, which has been designed to help a variety of research groups perform research, exploration and real-world demonstrations of brain-based, neuromorphic processors and hardware environments. A prototype kit has been built and tested. We explain the motivation behind the kit, its design and composition, and a prototype physical demonstration.

神经科学方面的巨大努力正在努力绘制许多新物种的连接群，包括果蝇果蝇的接近完成。重要的是要问这些模型是否可以使人工智能受益。在这项工作中，我们提出了两个基本问题：（1）生物连接组可以在机器学习中提供的何处以及何时提供使用，（2）哪些设计原理对于提取连接组的良好表示是必要的。为此，我们将秀丽隐杆线虫线虫的运动电路转化为以不同水平的生物物理现实主义水平的人工神经网络，并评估了这些网络在运动和非运动行为任务上训练这些网络的结果。我们证明，生物物理现实主义不必维持使用生物回路的优势。我们还确定，即使没有保留确切的接线图，建筑统计数据也提供了有价值的先验。最后，我们表明，虽然秀丽隐杆线虫运动电路对运动问题提供了强大的感应偏见，但其结构可能会阻碍与运动无关的任务（例如视觉分类问题）。

神经形态计算机通过模拟人脑进行计算，并使用极低的功率。预计将来对于节能计算是必不可少的。尽管它们主要用于尖峰基于神经网络的机器学习应用程序，但已知神经形态计算机是Turing-Complete，因此能够进行通用计算。但是，为了充分意识到它们的通用，节能计算的潜力，重要的是要设计有效的编码数字机制。当前的编码方法的适用性有限，可能不适合通用计算。在本文中，我们将虚拟神经元视为整数和理性数字的编码机制。我们评估虚拟神经元在物理和模拟神经形态硬件上的性能，并表明它可以使用基于混合信号的Memristor神经形态处理器平均使用23 nj的能量执行加法操作。我们还通过在某些MU回复功能中使用它来证明其实用性，这些功能是通用计算的构建块。

在本文中，我们介绍了RISP，这是一种减少的指令尖峰处理器。虽然大多数尖峰神经处理器都是基于大脑或大脑的概念，但我们为简化而不是复杂的尖峰处理器提供了案例。因此，它具有离散的集成周期，可配置的泄漏等等。我们介绍了RISP的计算模型，并突出了其简单性的好处。我们展示了它如何帮助开发用于简单计算任务的手部神经网络，并详细介绍如何使用它来简化使用更复杂的机器学习技术构建的神经网络，并演示其与其他尖峰神经过程相似的性能。

This paper utilizes an anomaly detection algorithm to check if underwater gliders are operating normally in the unknown ocean environment. Glider pilots can be warned of the detected glider anomaly in real time, thus taking over the glider appropriately and avoiding further damage to the glider. The adopted algorithm is validated by two valuable sets of data in real glider deployments, the University of South Florida (USF) glider Stella and the Skidaway Institute of Oceanography (SkIO) glider Angus.

Are extralinguistic signals such as image pixels crucial for inducing constituency grammars? While past work has shown substantial gains from multimodal cues, we investigate whether such gains persist in the presence of rich information from large language models (LLMs). We find that our approach, LLM-based C-PCFG (LC-PCFG), outperforms previous multi-modal methods on the task of unsupervised constituency parsing, achieving state-of-the-art performance on a variety of datasets. Moreover, LC-PCFG results in an over 50% reduction in parameter count, and speedups in training time of 1.7x for image-aided models and more than 5x for video-aided models, respectively. These results challenge the notion that extralinguistic signals such as image pixels are needed for unsupervised grammar induction, and point to the need for better text-only baselines in evaluating the need of multi-modality for the task.

In intensively managed forests in Europe, where forests are divided into stands of small size and may show heterogeneity within stands, a high spatial resolution (10 - 20 meters) is arguably needed to capture the differences in canopy height. In this work, we developed a deep learning model based on multi-stream remote sensing measurements to create a high-resolution canopy height map over the "Landes de Gascogne" forest in France, a large maritime pine plantation of 13,000 km$^2$ with flat terrain and intensive management. This area is characterized by even-aged and mono-specific stands, of a typical length of a few hundred meters, harvested every 35 to 50 years. Our deep learning U-Net model uses multi-band images from Sentinel-1 and Sentinel-2 with composite time averages as input to predict tree height derived from GEDI waveforms. The evaluation is performed with external validation data from forest inventory plots and a stereo 3D reconstruction model based on Skysat imagery available at specific locations. We trained seven different U-net models based on a combination of Sentinel-1 and Sentinel-2 bands to evaluate the importance of each instrument in the dominant height retrieval. The model outputs allow us to generate a 10 m resolution canopy height map of the whole "Landes de Gascogne" forest area for 2020 with a mean absolute error of 2.02 m on the Test dataset. The best predictions were obtained using all available satellite layers from Sentinel-1 and Sentinel-2 but using only one satellite source also provided good predictions. For all validation datasets in coniferous forests, our model showed better metrics than previous canopy height models available in the same region.

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs. The only human oversight is provided through a list of rules or principles, and so we refer to the method as 'Constitutional AI'. The process involves both a supervised learning and a reinforcement learning phase. In the supervised phase we sample from an initial model, then generate self-critiques and revisions, and then finetune the original model on revised responses. In the RL phase, we sample from the finetuned model, use a model to evaluate which of the two samples is better, and then train a preference model from this dataset of AI preferences. We then train with RL using the preference model as the reward signal, i.e. we use 'RL from AI Feedback' (RLAIF). As a result we are able to train a harmless but non-evasive AI assistant that engages with harmful queries by explaining its objections to them. Both the SL and RL methods can leverage chain-of-thought style reasoning to improve the human-judged performance and transparency of AI decision making. These methods make it possible to control AI behavior more precisely and with far fewer human labels.

This paper introduces corpus-guided top-down synthesis as a mechanism for synthesizing library functions that capture common functionality from a corpus of programs in a domain specific language (DSL). The algorithm builds abstractions directly from initial DSL primitives, using syntactic pattern matching of intermediate abstractions to intelligently prune the search space and guide the algorithm towards abstractions that maximally capture shared structures in the corpus. We present an implementation of the approach in a tool called Stitch and evaluate it against the state-of-the-art deductive library learning algorithm from DreamCoder. Our evaluation shows that Stitch is 3-4 orders of magnitude faster and uses 2 orders of magnitude less memory while maintaining comparable or better library quality (as measured by compressivity). We also demonstrate Stitch's scalability on corpora containing hundreds of complex programs that are intractable with prior deductive approaches and show empirically that it is robust to terminating the search procedure early -- further allowing it to scale to challenging datasets by means of early stopping.