Cellular automata are synchronous discrete dynamical systems used to describe complex dynamic behaviors. The dynamic is based on local interactions between the components, these are defined by a finite graph with an initial node coloring with two colors. In each step, all nodes change their current color synchronously to the least/most frequent color in their neighborhood and in case of a tie, keep their current color. After a finite number of rounds these systems either reach a fixed point or enter a 2-cycle. The problem of counting the number of fixed points for cellular automata is #P-complete. In this paper we consider cellular automata defined by a tree. We propose an algorithm with run-time $O(n\Delta)$ to count the number of fixed points, here $\Delta$ is the maximal degree of the tree. We also prove upper and lower bounds for the number of fixed points. Furthermore, we obtain corresponding results for pure cycles, i.e., instances where each node changes its color in every round. We provide examples demonstrating that the bounds are sharp. The results are proved for the minority and the majority model.
相關內容
Anomaly detection requires detecting abnormal samples in large unlabeled datasets. While progress in deep learning and the advent of foundation models has produced powerful zero-shot anomaly detection methods, their deployment in practice is often hindered by the lack of labeled data -- without it, their detection performance cannot be evaluated reliably. In this work, we propose SWSA (Selection With Synthetic Anomalies): a general-purpose framework to select image-based anomaly detectors with a generated synthetic validation set. Our proposed anomaly generation method assumes access to only a small support set of normal images and requires no training or fine-tuning. Once generated, our synthetic validation set is used to create detection tasks that compose a validation framework for model selection. In an empirical study, we find that SWSA often selects models that match selections made with a ground-truth validation set, resulting in higher AUROCs than baseline methods. We also find that SWSA selects prompts for CLIP-based anomaly detection that outperform baseline prompt selection strategies on all datasets, including the challenging MVTec-AD and VisA datasets.
Generative adversarial networks constitute a powerful approach to generative modeling. While generated samples often are indistinguishable from real data, mode-collapse may occur and there is no guarantee that they will follow the true data distribution. For scientific applications in particular, it is essential that the true distribution is well captured by the generated distribution. In this work, we propose a method to ensure that the distributions of certain generated data statistics coincide with the respective distributions of the real data. In order to achieve this, we add a new loss term to the generator loss function, which quantifies the difference between these distributions via suitable f-divergences. Kernel density estimation is employed to obtain representations of the true distributions, and to estimate the corresponding generated distributions from minibatch values at each iteration. When compared to other methods, our approach has the advantage that the complete shapes of the distributions are taken into account. We evaluate the method on a synthetic dataset and a real-world dataset and demonstrate improved performance of our approach.
There is increasing focus on adapting predictive models into agent-like systems, most notably AI assistants based on language models. We outline two structural reasons for why these models can fail when turned into agents. First, we discuss auto-suggestive delusions. Prior work has shown theoretically that models fail to imitate agents that generated the training data if the agents relied on hidden observations: the hidden observations act as confounding variables, and the models treat actions they generate as evidence for nonexistent observations. Second, we introduce and formally study a related, novel limitation: predictor-policy incoherence. When a model generates a sequence of actions, the model's implicit prediction of the policy that generated those actions can serve as a confounding variable. The result is that models choose actions as if they expect future actions to be suboptimal, causing them to be overly conservative. We show that both of those failures are fixed by including a feedback loop from the environment, that is, re-training the models on their own actions. We give simple demonstrations of both limitations using Decision Transformers and confirm that empirical results agree with our conceptual and formal analysis. Our treatment provides a unifying view of those failure modes, and informs the question of why fine-tuning offline learned policies with online learning makes them more effective.
An important prerequisite for autonomous robots is their ability to reliably grasp a wide variety of objects. Most state-of-the-art systems employ specialized or simple end-effectors, such as two-jaw grippers, which limit the range of objects to manipulate. Additionally, they conventionally require a structured and fully predictable environment while the vast majority of our world is complex, unstructured, and dynamic. This paper presents a novel approach to integrate a five-finger hand with visual servo control to enable dynamic grasping and compensate for external disturbances. The multi-fingered end-effector enhances the variety of possible grasps and manipulable objects. It is controlled by a deep learning based generative grasping network. The required virtual model of the unknown target object is iteratively completed by processing visual sensor data. Our experiments on real hardware confirm the system's capability to reliably grasp unknown dynamic target objects. To the best of our knowledge, this is the first method to achieve dynamic multi-fingered grasping for unknown objects. A video of the experiments is available at //youtu.be/5Ou6V_QMrNY.
High-resolution semantic segmentation requires substantial computational resources. Traditional approaches in the field typically downscale the input images before processing and then upscale the low-resolution outputs back to their original dimensions. While this strategy effectively identifies broad regions, it often misses finer details. In this study, we demonstrate that a streamlined model capable of directly producing high-resolution segmentations can match the performance of more complex systems that generate lower-resolution results. By simplifying the network architecture, we enable the processing of images at their native resolution. Our approach leverages a bottom-up information propagation technique across various scales, which we have empirically shown to enhance segmentation accuracy. We have rigorously tested our method using leading-edge semantic segmentation datasets. Specifically, for the Cityscapes dataset, we further boost accuracy by applying the Noisy Student Training technique.
The perception that the convergence of biological engineering and artificial intelligence (AI) could enable increased biorisk has recently drawn attention to the governance of biotechnology and artificial intelligence. The 2023 Executive Order, Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence, requires an assessment of how artificial intelligence can increase biorisk. Within this perspective, we present a simplistic framework for evaluating biorisk and demonstrate how this framework falls short in achieving actionable outcomes for a biorisk manager. We then suggest a potential path forward that builds upon existing risk characterization work and justify why characterization efforts of AI-enabled tools for engineering biology is needed.
Camera calibration is a crucial step in robotics and computer vision. Accurate camera parameters are necessary to achieve robust applications. Nowadays, camera calibration process consists of adjusting a set of data to a pin-hole model, assuming that with a reprojection error close to cero, camera parameters are correct. Since all camera parameters are unknown, computed results are considered true. However, the pin-hole model does not represent the camera behavior accurately if the focus is considered. Real cameras change the focal length slightly to obtain sharp objects in the image and this feature skews the calibration result if a unique pin-hole model is computed with a constant focal length. In this paper, a deep analysis of the camera calibration process is done to detect and strengthen its weaknesses. The camera is mounted in a robot arm to known extrinsic camera parameters with accuracy and to be able to compare computed results with the true ones. Based on the bias that exist between computed results and the true ones, a modification of the widely accepted camera calibration method using images of a planar template is presented. A pin-hole model with distance dependent focal length is proposed to improve the calibration process substantially
Sheaves are mathematical objects consisting of a base which constitutes a topological space and the data associated with each open set thereof, e.g. continuous functions defined on the open sets. Sheaves have originally been used in algebraic topology and logic. Recently, they have also modelled events such as physical experiments and natural language disambiguation processes. We extend the latter models from lexical ambiguities to discourse ambiguities arising from anaphora. To begin, we calculated a new measure of contextuality for a dataset of basic anaphoric discourses, resulting in a higher proportion of contextual models--82.9%--compared to previous work which only yielded 3.17% contextual models. Then, we show how an extension of the natural language processing challenge, known as the Winograd Schema, which involves anaphoric ambiguities can be modelled on the Bell-CHSH scenario with a contextual fraction of 0.096.
We propose a comprehensive sample-based method for assessing the quality of generative models. The proposed approach enables the estimation of the probability that two sets of samples are drawn from the same distribution, providing a statistically rigorous method for assessing the performance of a single generative model or the comparison of multiple competing models trained on the same dataset. This comparison can be conducted by dividing the space into non-overlapping regions and comparing the number of data samples in each region. The method only requires samples from the generative model and the test data. It is capable of functioning directly on high-dimensional data, obviating the need for dimensionality reduction. Significantly, the proposed method does not depend on assumptions regarding the density of the true distribution, and it does not rely on training or fitting any auxiliary models. Instead, it focuses on approximating the integral of the density (probability mass) across various sub-regions within the data space.
While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite complex. Despite this, the most widely used perceptual metrics today, such as PSNR and SSIM, are simple, shallow functions, and fail to account for many nuances of human perception. Recently, the deep learning community has found that features of the VGG network trained on the ImageNet classification task has been remarkably useful as a training loss for image synthesis. But how perceptual are these so-called "perceptual losses"? What elements are critical for their success? To answer these questions, we introduce a new Full Reference Image Quality Assessment (FR-IQA) dataset of perceptual human judgments, orders of magnitude larger than previous datasets. We systematically evaluate deep features across different architectures and tasks and compare them with classic metrics. We find that deep features outperform all previous metrics by huge margins. More surprisingly, this result is not restricted to ImageNet-trained VGG features, but holds across different deep architectures and levels of supervision (supervised, self-supervised, or even unsupervised). Our results suggest that perceptual similarity is an emergent property shared across deep visual representations.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191