Pseudo-rehearsal allows neural networks to learn a sequence of tasks without forgetting how to perform in earlier tasks. Preventing forgetting is achieved by introducing a generative network which can produce data from previously seen tasks so that it can be rehearsed along side learning the new task. This has been found to be effective in both supervised and reinforcement learning. Our current work aims to further prevent forgetting by encouraging the generator to accurately generate features important for task retention. More specifically, the generator is improved by introducing a second discriminator into the Generative Adversarial Network which learns to classify between real and fake items from the intermediate activation patterns that they produce when fed through a continual learning agent. Using Atari 2600 games, we experimentally find that improving the generator can considerably reduce catastrophic forgetting compared to the standard pseudo-rehearsal methods used in deep reinforcement learning. Furthermore, we propose normalising the Q-values taught to the long-term system as we observe this substantially reduces catastrophic forgetting by minimising the interference between tasks' reward functions.

Responding to the need for semantic lexical resources in natural language processing applications, we examine methods to acquire noun compounds (NCs), e.g., "orange juice", together with suitable fine-grained semantic interpretations, e.g., "squeezed from", which are directly usable as paraphrases. We employ bootstrapping and web statistics, and utilize the relationship between NCs and paraphrasing patterns to jointly extract NCs and such patterns in multiple alternating iterations. In evaluation, we found that having one compound noun fixed yields both a higher number of semantically interpreted NCs and improved accuracy due to stronger semantic restrictions.

Automated reasoning and theorem proving have recently become major challenges for machine learning. In other domains, representations that are able to abstract over unimportant transformations, such as abstraction over translations and rotations in vision, are becoming more common. Standard methods of embedding mathematical formulas for learning theorem proving are however yet unable to handle many important transformations. In particular, embedding previously unseen labels, that often arise in definitional encodings and in Skolemization, has been very weak so far. Similar problems appear when transferring knowledge between known symbols. We propose a novel encoding of formulas that extends existing graph neural network models. This encoding represents symbols only by nodes in the graph, without giving the network any knowledge of the original labels. We provide additional links between such nodes that allow the network to recover the meaning and therefore correctly embed such nodes irrespective of the given labels. We test the proposed encoding in an automated theorem prover based on the tableaux connection calculus, and show that it improves on the best characterizations used so far. The encoding is further evaluated on the premise selection task and a newly introduced symbol guessing task, and shown to correctly predict 65% of the symbol names.

SINGAPORE - Singapore-based regulatory technology firm Tookitaki has raised US$19.2 million (S$26.1 million) in Series A funding as it seeks to expand its presence in international markets. The company has received $11.7 million in investment, adding to the $7.5 million raised earlier this year. A group, led by Viola Fintech and SIG Asia Investment, was responsible for the fresh injection of funds, which will help Tookitaki increase its employee headcount across its three offices in Singapore, India and the United States by up to 100 per cent, as well as to fine-tune its products. "Our vision has always been for our compliance technology to become globally accepted by financial institutions around the world, and (the investments) put us in a better place to deliver on that vision," said Tookitaki co-founder and chief executive officer Abhishek Chatterjee on Monday (Nov 25) Tookitaki offers two artificial intelligence-powered software platforms. The first is an anti-money laundering solution that aims to help banks better monitor and detect suspicious transactions, and comply with regulatory requirements.

In this article, the epistemic-entrenchment and partial-meet characterizations of Parikh's relevance-sensitive axiom for belief revision, known as axiom (P), are provided. In short, axiom (P) states that, if a belief set $K$ can be divided into two disjoint compartments, and the new information $\varphi$ relates only to the first compartment, then the revision of $K$ by $\varphi$ should not affect the second compartment. Accordingly, we identify the subclass of epistemic-entrenchment and that of selection-function preorders, inducing AGM revision functions that satisfy axiom (P). Hence, together with the faithful-preorders characterization of (P) that has already been provided, Parikh's axiom is fully characterized in terms of all popular constructive models of Belief Revision. Since the notions of relevance and local change are inherent in almost all intellectual activity, the completion of the constructive view of (P) has a significant impact on many theoretical, as well as applied, domains of Artificial Intelligence.

Growing number of network devices and services have led to increasing demand for protective measures as hackers launch attacks to paralyze or steal information from victim systems. Intrusion Detection System (IDS) is one of the essential elements of network perimeter security which detects the attacks by inspecting network traffic packets or operating system logs. While existing works demonstrated effectiveness of various machine learning techniques, only few of them utilized the time-series information of network traffic data. Also, categorical information has not been included in neural network based approaches. In this paper, we propose network intrusion detection models based on sequential information using long short-term memory (LSTM) network and categorical information using the embedding technique. We have experimented the models with UNSW-NB15, which is a comprehensive network traffic dataset. The experiment results confirm that the proposed method improve the performance, observing binary classification accuracy of 99.72\%.

Recurrent neural networks (RNN) have been successfully applied to various sequential decision-making tasks, natural language processing applications, and time-series predictions. Such networks are usually trained through back-propagation through time (BPTT) which is prohibitively expensive, especially when the length of the time dependencies and the number of hidden neurons increase. To reduce the training time, extreme learning machines (ELMs) have been recently applied to RNN training, reaching a 99\% speedup on some applications. Due to its non-iterative nature, ELM training, when parallelized, has the potential to reach higher speedups than BPTT. In this work, we present \opt, an optimized parallel RNN training algorithm based on ELM that takes advantage of the GPU shared memory and of parallel QR factorization algorithms to efficiently reach optimal solutions. The theoretical analysis of the proposed algorithm is presented on six RNN architectures, including LSTM and GRU, and its performance is empirically tested on ten time-series prediction applications. \opt~is shown to reach up to 845 times speedup over its sequential counterpart and to require up to 20x less time to train than parallel BPTT.

Scaling Bayesian optimisation (BO) to high-dimensional search spaces is a active and open research problems particularly when no assumptions are made on function structure. The main reason is that at each iteration, BO requires to find global maximisation of acquisition function, which itself is a non-convex optimization problem in the original search space. With growing dimensions, the computational budget for this maximisation gets increasingly short leading to inaccurate solution of the maximisation. This inaccuracy adversely affects both the convergence and the efficiency of BO. We propose a novel approach where the acquisition function only requires maximisation on a discrete set of low dimensional subspaces embedded in the original high-dimensional search space. Our method is free of any low dimensional structure assumption on the function unlike many recent high-dimensional BO methods. Optimising acquisition function in low dimensional subspaces allows our method to obtain accurate solutions within limited computational budget. We show that in spite of this convenience, our algorithm remains convergent. In particular, cumulative regret of our algorithm only grows sub-linearly with the number of iterations. More importantly, as evident from our regret bounds, our algorithm provides a way to trade the convergence rate with the number of subspaces used in the optimisation. Finally, when the number of subspaces is "sufficiently large", our algorithm's cumulative regret is at most $\mathcal{O}^{*}(\sqrt{T\gamma_T})$ as opposed to $\mathcal{O}^{*}(\sqrt{DT\gamma_T})$ for the GP-UCB of Srinivas et al. (2012), reducing a crucial factor $\sqrt{D}$ where $D$ being the dimensional number of input space.

Abstract--Privacy issues related to video camera feeds have led to a growing need for suitable alternatives that provide functionalities such as user authentication, activity cla ssification and tracking in a noninvasive manner . Existing infrastruct ure makes Wi-Fi a possible candidate, yet, utilizing tradition al signal processing methods to extract information necessary to ful ly characterize an event by sensing weak ambient Wi-Fi signals is deemed to be challenging. This paper introduces a novel en d-to-end deep learning framework that simultaneously predic ts the identity, activity and the location of a user to create user p rofiles similar to the information provided through a video camera. The system is fully autonomous and requires zero user intervent ion unlike systems that require user-initiated initializatio n, or a user held transmitting device to facilitate the prediction. The system can also predict the trajectory of the user by predicting the location of a user over consecutive time steps. The performa nce of the system is evaluated through experiments. P ARTfrom the applications related to surveillance and defense, user identification, behaviour analysis, localization and user activity recognition have become increasingly crucial tasks due to the popularity of facilities such as cashierless stores and senior citizen residences. Current state-of-the-art techniques for passive user authentication [1], re-identification [2], activity classification [3] and trackin g [4], [5] are primarily based on video feed analysis. However, due to concerns on privacy invasion, camera videos are not deeme d to be the best choice in many practical applications. Hence, there is a growing need for noninvasive alternatives. A possible alternative being considered is ambient Wi-Fi signals, which are widely available and easily accessible.

Noname manuscript No. (will be inserted by the editor) Abstract We formalize networks with evolving structures as temporal networks and propose a generative link prediction model, Generative Link Sequence Modeling (GLSM), to predict future links for temporal networks. GLSM captures the temporal link formation patterns from the observed links with a sequence modeling framework and has the ability to generate the emerging links by inferring from the probability distribution on the potential future links. To avoid overfitting caused by treating each link as a unique token, we propose a self-tokenization mechanism to transform each raw link in the network to an abstract aggregation token automatically. The self-tokenization is seamlessly integrated into the sequence modeling framework, which allows the proposed GLSM model to have the generalization capability to discover link formation patterns beyond raw link sequences. We compare GLSM with the existing state-of-art methods on five real-world datasets. The experimental results demonstrate that GLSM obtains future positive links effectively in a generative fashion while achieving the best performance (2-10% improvements on AUC) among other alternatives. Keywords Temporal link prediction, sequence modeling, recurrent neural network, self-tokenization mechanism 1 Introduction Many real-world applications could be modeled as link prediction problems. Lu Bai is the corresponding author, Email: bailucs@cufe.edu.cn 1. Central University of Finance and Economics, Beijing, P.R. China. Two mainstream categories in link prediction are either based on the statistical patterns of the link formation behaviors of the network [10, 2, 17] or the graph representation learning [31, 33] methods which embed nodes as vectors with respect to the network topological information. Most of these methods are discriminative models that verify whether an unknown link given during the test time is rational by training a classifier on existing links and negative samples [19].