Unlike the uniform application of asingle penalty,CPR enforces an upper bound on astatistical measure, suchas theL2-norm, ofindividual parameter matrices.

We introduce a novel segmentation-aware joint training framework called generative reinforcement network (GRN) that integrates segmentation loss feedback to optimize both image generation and segmentation performance in a single stage. An image enhancement technique called segmentation-guided enhancement (SGE) is also developed, where the generator produces images tailored specifically for the segmentation model. Two variants of GRN were also developed, including GRN for sample-efficient learning (GRN-SEL) and GRN for semi-supervised learning (GRN-SSL). GRN's performance was evaluated using a dataset of 69 fully annotated 3D ultrasound scans from 29 subjects. The annotations included six anatomical structures: dermis, superficial fat, superficial fascial membrane (SFM), deep fat, deep fascial membrane (DFM), and muscle. Our results show that GRN-SEL with SGE reduces labeling efforts by up to 70% while achieving a 1.98% improvement in the Dice Similarity Coefficient (DSC) compared to models trained on fully labeled datasets. GRN-SEL alone reduces labeling efforts by 60%, GRN-SSL with SGE decreases labeling requirements by 70%, and GRN-SSL alone by 60%, all while maintaining performance comparable to fully supervised models. These findings suggest the effectiveness of the GRN framework in optimizing segmentation performance with significantly less labeled data, offering a scalable and efficient solution for ultrasound image analysis and reducing the burdens associated with data annotation.

This work addresses weight optimization problem for fully-connected feed-forward neural networks. Unlike existing approaches that are based on back-propagation (BP) and chain rule gradient-based optimization (which implies iterative execution, potentially burdensome and time-consuming in some cases), the proposed approach offers the solution for weight optimization in closed-form by means of least squares (LS) methodology. In the case where the input-to-output mapping is injective, the new approach optimizes the weights in a back-propagating fashion in a single iteration by jointly optimizing a set of weights in each layer for each neuron. In the case where the input-to-output mapping is not injective (e.g., in classification problems), the proposed solution is easily adapted to obtain its final solution in a few iterations. An important advantage over the existing solutions is that these computations (for all neurons in a layer) are independent from each other; thus, they can be carried out in parallel to optimize all weights in a given layer simultaneously. Furthermore, its running time is deterministic in the sense that one can obtain the exact number of computations necessary to optimize the weights in all network layers (per iteration, in the case of non-injective mapping). Our simulation and empirical results show that the proposed scheme, BPLS, works well and is competitive with existing ones in terms of accuracy, but significantly surpasses them in terms of running time. To summarize, the new method is straightforward to implement, is competitive and computationally more efficient than the existing ones, and is well-tailored for parallel implementation.

There is a debate in the world of cybersecurity about whether to use human or machine expertise. However, this is a false dichotomy: Truly effective threat detection and response need both kinds of expertise working in tandem. It will be years before machines completely replace the humans who perform typical detection and response tasks. What we predict for the meantime is a symbiotic relationship between humans and machines. The combination means that detection of and response to threats can be faster and more intelligent.

There will be many people who will say it does exist and has working technologies, hardware and software. It is an interesting error in thinking to focus on closed system devices/products as to what Ubiquity (IoT3) is. Devices are used to get across the point of various types of connections and networks being accessed. But more importantly in a full implementation of the concept of Ubiquity (often described as the IoT) devices may not even be owned anymore. The ownership of devices ceases to be important if you can own your digital identity, can verify it and establish your own ecosystem of assets in Blockchain.

Artificial intelligence (AI), machine learning and cognitive analytics are having a tremendous impact in areas ranging from medical diagnostics to self-driving cars. AI systems are highly dependent on enormous volumes of data--both at rest in repositories and in motion in real time--to learn from experience, make connections and arrive at critical business decisions. Usage of AI is also expected to expand significantly in the not-so-distant future. As a result, having the right storage to support the massive amounts of data required for AI workloads is an important consideration for an increasing number of organizations. Availability: When a business leader uses AI for critical tasks such as understanding how best to run their manufacturing process or to optimize their supply chain, they cannot afford to risk any loss of availability in the supporting storage system.

My Computer Is an Honor Student -- But How Intelligent Is It? Standardized Tests as a Measure of AI Given the well-known limitations of the Turing test, there is a need for objective tests to both focus attention on, and measure progress toward, the goals of AI. In this paper we argue that machine performance on standardized tests should be a key component of any new measure of AI, because attaining a high level of performance requires solving significant AI problems involving language understanding and world modeling -- critical skills for any machine that lays claim to intelligence. In addition, standardized tests have all the basic requirements of a practical test: they are accessible, easily comprehensible, clearly measurable, and offer a graduated progression from simple tasks to those requiring deep understanding of the world. Here we propose this task as a challenge problem for the community, summarize our state-of-the-art results on math and science tests, and provide supporting data sets (www.allenai.org). In the years since, this test has been criticized as being a poor replacement for the original enquiry (for example, Hayes and Ford [1995]), which raises the question: what would a better replacement be?

Recent years have seen significant technical progress on robot planning, enabling robots to compute actions and motions to accomplish challenging tasks involving driving, flying, walking, or manipulating objects. However, robots that have been commercially deployed in the real world typically have no or minimal planning capability. These robots are often manually programmed, teleoperated, or programmed to follow simple rules. Although these robots are highly successful in their respective niches, a lack of planning capabilities limits the range of tasks for which currently deployed robots can be used. In this article, we highlight key conclusions from a workshop sponsored by the National Science Foundation in October 2013 that summarize opportunities and key challenges in robot planning and include challenge problems identified in the workshop that can help guide future research toward making robot planning more deployable in the real world.

The purpose of the meeting was to assist ARPA in defining an agenda for foundational AI research. Prior to the meeting, the fellows and officers of AAAI, as well as the report committee members, were asked to recommend areas in which major research thrusts could yield significant scientific gain--with high potential impact on DOD applications--over the next ten years. At the meeting, these suggestions and their relevance to current national needs and challenges in computing were discussed and debated. An initial draft of this report was circulated to the fellows and officers. The final report has benefited greatly from their comments and from textual revisions contributed by Joseph Halpern, Fernando Pereira, and Dana Nau. Computer systems are becoming commonplace; indeed, they are almost ubiquitous. We find them central to the functioning of most business, governmental, military, environmental, and healthcare organizations. They are also a part of many educational and training ...

We built on previous work to develop an evaluation method that can be used to select expert system applications which are most likely to be successfully implemented. Both essential and desirable features of an expert system application are discussed. Essential features are used to ensure that the application does not require technology beyond the state of the art. Advice on helpful directions for evaluating candidate expert system applications is also given. If expert systems are to withstand this transition, special attention must be paid to the applications that are selected to test the real-world impact of this technology.