Indonesian schools and universities were forced to suddenly changed from conventional classroom to full online classroom in late March 2020 to combat the spread of COVID19. the change has not been easy for many, yet i...
详细信息
the principle of optimality in decision-making for games with nature, based on assessments of efficiency and risk, is proposed. In contrast to the traditional approach to the definition of a mixed strategy in game the...
详细信息
the learning with errors (LWE) problem is one of the fundamental problems in cryptography and it has many applications in post-quantum cryptography. there are two variants of the problem, the decisional-LWE problem, a...
详细信息
ISBN:
(数字)9783031376795
ISBN:
(纸本)9783031376788;9783031376795
the learning with errors (LWE) problem is one of the fundamental problems in cryptography and it has many applications in post-quantum cryptography. there are two variants of the problem, the decisional-LWE problem, and the search-LWE problem. LWE search-to-decision reduction shows that the hardness of the search-LWE problem can be reduced to the hardness of the decisional-LWE problem. the efficiency of the reduction can be regarded as the gap in difficulty between the problems. We initiate a study of quantum search-to-decision reduction for the LWE problem and propose a reduction that satisfies sample-preserving. In sample-preserving reduction, it preserves all parameters even the number of instances. Especially, our quantum reduction invokes the distinguisher only 2 times to solve the search-LWE problem, while classical reductions require a polynomial number of invocations. Furthermore, we give a way to amplify the success probability of the reduction algorithm. Our amplified reduction works with fewer LWE samples compared to the classical reduction that has a high success probability. Our reduction algorithm supports a wide class of error distributions and also provides a search-to-decision reduction for the learning parity with noise problem. In the process of constructing the search-to-decision reduction, we give a quantum Goldreich-Levin theorem over Z(q) where q is prime. In short, this theorem states that, if a hardcore predicate a center dot s (mod q) can be predicted with probability distinctly greater than 1/q with respect to a uniformly random a epsilon Z(q)(n), then it is possible to determine s epsilon Z(q)(n)
Tasks are of primary importance for artificial intelligence (AI), yet no theory about their characteristics exists. the kind of task theory we envision is one that allows an objective comparison of tasks, based on mea...
详细信息
ISBN:
(数字)9783030937584
ISBN:
(纸本)9783030937577;9783030937584
Tasks are of primary importance for artificial intelligence (AI), yet no theory about their characteristics exists. the kind of task theory we envision is one that allows an objective comparison of tasks, based on measurable physical properties, and that can serve as a foundation for studying, evaluating, and comparing learning controllers of various kinds on a variety of tasks by providing principled ways for constructing, comparing, and changing tasks with particular properties and levels of difficulty. In prior papers we have outlined an approach towards this goal;in this paper we present further principles for its development, including causal relations. We use these principles to expand our prior ideas, withthe aim of laying the groundwork for covering levels of detail, prior knowledge of the learner/performer and task difficulty, to name some of the complex issues that must be solved for a useful task theory.
Product embeddings have been heavily investigated in the past few years, serving as the cornerstone for a broad range of machine learning applications in e-commerce. Despite the empirical success of product embeddings...
详细信息
ISBN:
(纸本)9781450382977
Product embeddings have been heavily investigated in the past few years, serving as the cornerstone for a broad range of machine learning applications in e-commerce. Despite the empirical success of product embeddings, little is known on how and why they work from the theoretical standpoint. Analogous results from the natural language processing (NLP) often rely on domain-specific properties that are not transferable to the e-commerce setting, and the downstream tasks often focus on different aspects of the embeddings. We take an e-commerce-oriented view of the product embeddings and reveal a complete theoretical view from boththe representation learning and the learningtheory perspective. We prove that product embeddings trained by the widely-adopted skip-gram negative sampling algorithm and its variants are sufficient dimension reduction regarding a critical product relatedness measure. the generalization performance in the downstream machine learning task is controlled by the alignment between the embeddings and the product relatedness measure. Following the theoretical discoveries, we conduct exploratory experiments that supports our theoretical insights for the product embeddings.
the growth of medical device innovation over the last decades has necessitated the need for strong regulatory control in order to ensure the safety and performance of such devices. Medical devices are categorised acco...
详细信息
ISBN:
(纸本)9781450390118
the growth of medical device innovation over the last decades has necessitated the need for strong regulatory control in order to ensure the safety and performance of such devices. Medical devices are categorised according to the risk posed to the public. However, the legislation describing the classification rules are often dense and difficult to read. In order to facilitate device classification, the medical device regulator in Australia, the therapeutic Goods Authority (TGA), provides online digital support tool for device classification. In this work, we (i) evaluate the online tool and (ii) make a further a proposal for using machine learning as means to provide more effective results. For the first part of this work, we asses whether the tool increases the readability of the legislative rules by evaluating the Flesch reading ease score of the legislation and the tool. While the online tool provides some degree of simplicity and readability over the legislation, we argue that the TGA can make more use of its data in order to provide more effective services. In the second part, we develop a proof-of-concept machine learning model to classify a device based on its stated purpose. the results of the experiment show a 82% weighted accuracy across four class labels, indicating that a more data-driven approach could be adopted by the authority.
As artificial intelligence-empowered applications flourish and machine learning methodologies are commonly used to process large chunks of data and make decisions, the need for explainable artificial intelligence is b...
As artificial intelligence-empowered applications flourish and machine learning methodologies are commonly used to process large chunks of data and make decisions, the need for explainable artificial intelligence is becoming ever more pressing. In this work, we present results from a survey we conducted on the level of adoption of artificial intelligence-empowered applications by physicians. Next, we employ the diffusion of Innovation theory to determine what kind of adopters the doctors are and thus outline an implementation strategy and the level and depth of required explainability.
Many courses from Chinese Universities have to change the teaching model and content in suit for distance learning because of COVID-19 pandemic. this paper indicates a virtual learning community called Digital Philoso...
详细信息
Edward C. Tolman found reinforcement learning unsatisfactory for explaining intelligence and proposed a clear distinction between learning and behavior. Tolman's ideas on latent learning and cognitive maps eventua...
详细信息
ISBN:
(数字)9783030937584
ISBN:
(纸本)9783030937577;9783030937584
Edward C. Tolman found reinforcement learning unsatisfactory for explaining intelligence and proposed a clear distinction between learning and behavior. Tolman's ideas on latent learning and cognitive maps eventually led to what is now known as conceptual space, a geometric representation where concepts and ideas can form points or shapes. Active navigation between ideas - reasoning - can be expressed directly as purposive navigation in conceptual space. Assimilating the theory of conceptual space from modern neuroscience, we propose autonomous navigation as a valid approach for emulated cognition. However, achieving autonomous navigation in high-dimensional Euclidean spaces is not trivial in technology. In this work, we explore whether neoRL navigation is up for the task;adopting Kaelbling's concerns for efficient robot navigation, we test whether the neoRL approach is general across navigational modalities, compositional across considerations of experience, and effective when learning in multiple Euclidean dimensions. We find neoRL learning to be more resemblant of biological learningthan of RL in AI, and propose neoRL navigation of conceptual space as a plausible new path toward emulated cognition.
this study focussed on the utilisation of interactive simulations in the teaching and learning of a Grade 10 Chemistry topic (three states of matter [TSM]) - specifically sub-microscopic behaviour of particles - in th...
详细信息
暂无评论