In this paper we propose a method to model speaker and session variability and able to generate likelihood ratios using neural networks in an end-to-end phrase dependent speaker verification system. As in Joint Factor Analysis, the model uses tied hidden variables to model speaker and session variability and a MAP adaptation of some of the parameters of the model. In the training procedure our method jointly estimates the network parameters and the values of the speaker and channel hidden variables. This is done in a two-step backpropagation algorithm, first the network weights and factor loading matrices are updated and then the hidden variables, whose gradients are calculated by aggregating the corresponding speaker or session frames, since these hidden variables are tied. The last layer of the network is defined as a linear regression probabilistic model whose inputs are the previous layer outputs. This choice has the advantage that it produces likelihoods and additionally it can be adapted during the enrolment using MAP without the need of a gradient optimization. The decisions are made based on the ratio of the output likelihoods of two neural network models, speaker adapted and universal background model. The method was evaluated on the RSR2015 database.

Recent research about margin theory has proved that maximizing the minimum margin like support vector machines does not necessarily lead to better performance, and instead, it is crucial to optimize the margin distribution. In the meantime, margin theory has been used to explain the empirical success of deep network in recent studies. In this paper, we present mdNet (the Optimal Margin Distribution Network), a network which embeds a loss function in regard to the optimal margin distribution. We give a theoretical analysis of our method using the PAC-Bayesian framework, which confirms the significance of the margin distribution for classification within the framework of deep networks. In addition, empirical results show that the mdNet model always outperforms the baseline cross-entropy loss model consistently across different regularization situations. And our mdNet model also outperforms the cross-entropy loss (Xent), hinge loss and soft hinge loss model in generalization task through limited training data.

Hierarchical temporal memory (HTM) is a biomimetic sequence memory algorithm that holds promise for invariant representations of spatial and spatiotemporal inputs. This paper presents a comprehensive neuromemristive crossbar architecture for the spatial pooler (SP) and the sparse distributed representation classifier, which are fundamental to the algorithm. There are several unique features in the proposed architecture that tightly link with the HTM algorithm. A memristor that is suitable for emulating the HTM synapses is identified and a new Z-window function is proposed. The architecture exploits the concept of synthetic synapses to enable potential synapses in the HTM. The crossbar for the SP avoids dark spots caused by unutilized crossbar regions and supports rapid on-chip training within 2 clock cycles. This research also leverages plasticity mechanisms such as neurogenesis and homeostatic intrinsic plasticity to strengthen the robustness and performance of the SP. The proposed design is benchmarked for image recognition tasks using MNIST and Yale faces datasets, and is evaluated using different metrics including entropy, sparseness, and noise robustness. Detailed power analysis at different stages of the SP operations is performed to demonstrate the suitability for mobile platforms.

When applying machine learning to sensitive data, one has to balance between accuracy, information leakage, and computational-complexity. Recent studies have shown that Homomorphic Encryption (HE) can be used for protecting against information leakage while applying neural networks. However, this comes with the cost of limiting the width and depth of neural networks that can be used (and hence the accuracy) and with latency of the order of several minutes even for relatively simple networks. In this study we provide two solutions that address these limitations. In the first solution, we present more than $10\times$ improvement in latency and enable inference on wider networks compared to prior attempts with the same level of security. The improved performance is achieved via a collection of methods to better represent the data during the computation. In the second solution, we apply the method of transfer learning to provide private inference services using deep networks with latency less than 0.2 seconds. We demonstrate the efficacy of our methods on several computer vision tasks.

Nonnegative CANDECOMP/PARAFAC (NCP) decomposition is an important tool to process nonnegative tensor. Sometimes, additional sparse regularization is needed to extract meaningful nonnegative and sparse components. Thus, an optimization method for NCP that can impose sparsity efficiently is required. In this paper, we construct NCP with sparse regularization (sparse NCP) by l1-norm. Several popular optimization methods in block coordinate descent framework are employed to solve the sparse NCP, all of which are deeply analyzed with mathematical solutions. We compare these methods by experiments on synthetic and real tensor data, both of which contain third-order and fourth-order cases. After comparison, the methods that have fast computation and high effectiveness to impose sparsity will be concluded. In addition, we proposed an accelerated method to compute the objective function and relative error of sparse NCP, which has significantly improved the computation of tensor decomposition especially for higher-order tensor.

A key issue in cooperative game theory is coalitional stability, usually captured by the notion of the core---the set of outcomes that are resistant to group deviations. However, some coalitional games have empty cores, and any outcome in such a game is unstable. We investigate the possibility of stabilizing a coalitional game by using subsidies. We consider scenarios where an external party that is interested in having the players work together offers a supplemental payment to the grand coalition, or, more generally, a particular coalition structure. This payment is conditional on players not deviating from this coalition structure, and may be divided among the players in any way they wish. We define the cost of stability as the minimum external payment that stabilizes the game. We provide tight bounds on the cost of stability, both for games where the coalitional values are nonnegative (profit-sharing games) and for games where the coalitional values are nonpositive (cost-sharing games), under natural assumptions on the characteristic function, such as superadditivity, anonymity, or both. We also investigate the relationship between the cost of stability and several variants of the least core. Finally, we study the computational complexity of problems related to the cost of stability, with a focus on weighted voting games.

In the multi-agent path finding problem (MAPF) we are given a set of agents each with respective start and goal positions. The task is to find paths for all agents while avoiding collisions aiming to minimize an objective function. Two such common objective functions is the sum-of-costs and the makespan. Many optimal solvers were introduced in the past decade - two prominent categories of solvers can be distinguished: search-based solvers and compilation-based solvers. Search-based solvers were developed and tested for the sum-of-costs objective while the most prominent compilation-based solvers that are built around Boolean satisfiability (SAT) were designed for the makespan objective. Very little was known on the performance and relevance of the compilation-based approach on the sum-of-costs objective. In this paper we show how to close the gap between these cost functions in the compilation-based approach. Moreover we study applicability of various techniques developed for search-based solvers in the compilation-based approach. A part of this paper introduces a SAT-solver that is directly aimed to solve the sum-of-costs objective function. Using both a lower bound on the sum-of-costs and an upper bound on the makespan, we are able to have a reasonable number of variables in our SAT encoding. We then further improve the encoding by borrowing ideas from ICTS, a search-based solver. Experimental evaluation on several domains show that there are many scenarios where our new SAT-based methods outperforms the best variants of previous sum-of-costs search solvers - the ICTS, CBS algorithms, and ICBS algorithms.

Quantum algorithm design lies in the hallmark of applications of quantum computation and quantum simulation. Here we put forward a deep reinforcement learning (RL) architecture for automated algorithm design in the framework of quantum adiabatic algorithm, where the optimal Hamiltonian path to reach a quantum ground state that encodes a compution problem is obtained by RL techniques. We benchmark our approach in Grover search and 3-SAT problems, and find that the adiabatic algorithm obtained by our RL approach leads to significant improvement in the success probability and computing speedups for both moderate and large number of qubits compared to conventional algorithms. The RL-designed algorithm is found to be qualitatively distinct from the linear algorithm in the resultant distribution of success probability. Considering the established complexity-equivalence of circuit and adiabatic quantum algorithms, we expect the RL-designed adiabatic algorithm to inspire novel circuit algorithms as well. Our approach offers a recipe to design quantum algorithms for generic problems through a machinery RL process, which paves a novel way to automated quantum algorithm design using artificial intelligence, potentially applicable to different quantum simulation and computation platforms from trapped ions and optical lattices to superconducting-qubit devices.

Britons could have lost hundreds of pounds through online scams over the Christmas period – and are set to be hit by even more attacks by the presents they have managed to buy. That is the warning from cyber security experts who see Christmas as one of the riskiest time of the year, with the rush to find bargains and last-minute deals leading people to malicious websites. Tens of billions of pounds have been spent online in the run-up to the Christmas period, but despite the growth of internet shopping, many customers are still running the risk of buying with unidentified and often unsafe websites. Brits – who together will spend nearly £25 billion over the Christmas period – are at risk of having £725 stolen from their accounts, according to the cyber security firm McAfee. Scams from such websites are often so significant they can lead to people cancelling Christmas, but shoppers are often enticed to them with the promise of saving money.

In 2018 the world saw a marriage of policy and technology to give consumers more control over their data. In 2019, as the relationship between humans and technology continues to become more intertwined, I believe we'll see an even more marked shift in how we deal with data, from stricter guidelines outlining how marketers can access it to a greater dependency on the devices we use to make sense of it. In 2019, marketers need to keep up or be left behind. In May, the EU took a major step toward protecting the digital rights and privacy of its citizens when it implemented GDPR, launching a new standard that changed how companies handle consumer privacy and gave people new rights to their own data. GDPR spawned an international awareness and conversation about data privacy, data mining and control over individual usage.