Such 2D representations have lower dimensionality than audio waveforms and they easily fit advanced deep learning architectures mainly developed for computer visi on applications. Mel frequency cepstral coefficient (MFCC), short-time Fourier transformation (STFT), discrete wavel et transformation (DWT) are among the most pervasive 2D signal representations which essentially visualize frequ ency-magnitude distribution of a given reconstructed signal ove r time. Thus far, the best sound classification accuracy has been achieved for deep learning algorithms trained on 2D signal representations [1, 2]. However, it has been shown th at despite achieving high performance, the approaches based on 2D representations are very vulnerable against adversar ial attacks [3]. Unfortunately, this poses a strict security is sue because crafted adversarial examples not only mislead the target model toward a wrong label, but also, they are transfe r-able to other models including conventional algorithms suc h as support vector machines (SVM) [3].

The holy grail in deep neural network research is porting the memory- and computation-intensive network models on embedded platforms with a minimal compromise in model accuracy. To this end, we propose a novel approach, termed as Variational Student, where we reap the benefits of compressibility of the knowledge distillation (KD) framework, and sparsity inducing abilities of variational inference (VI) techniques. Essentially, we build a sparse student network, whose sparsity is induced by the variational parameters found via optimizing a loss function based on VI, leveraging the knowledge learnt by an accurate but complex pre-trained teacher network. Further, for sparsity enhancement, we also employ a Block Sparse Regularizer on a concatenated tensor of teacher and student network weights. We demonstrate that the marriage of KD and the VI techniques inherits compression properties from the KD framework, and enhances levels of sparsity from the VI approach, with minimal compromise in the model accuracy. We benchmark our results on LeNet MLP and VGGNet (CNN) and illustrate a memory footprint reduction of 64x and 213x on these MLP and CNN variants, respectively, without a need to retrain the teacher network. Furthermore, in the low data regime, we observed that our method outperforms state-of-the-art Bayesian techniques in terms of accuracy.

When the cost of an operational test is expensive, it is desirable to Nagoya Institute of Technology † RIKEN Center for Advanced Intelligence Project ‡ National Institute for Materials Sciences § email:takeuchi.ichiro@nitech.ac.jp be able to identify the region of appropriate input conditions in as few operational tests as possible. If we regard the operational conditions as inputs and the results of the operational tests as outputs of a black-box function, this problem can be viewed as a type of active learning (AL) problem called Level Set Estimation (LSE) . LSE is defined as the problem of identifying the input region in which the outputs of a function are smaller/greater than a certain threshold. In the statistics and machine learning literature, many methods for the LSE problem have been proposed [Bryan et al., 2006, Gotovos et al., 2013, Zanette et al., 2018]. In practical manufacturing applications, since it is often difficult to accurately control the input conditions during the actual usage of the machine, there is a need to guarantee the performance of the machine after properly incorporating the possible variation of input conditions.

Recently, the \textit{Tensor Nuclear Norm~(TNN)} regularization based on t-SVD has been widely used in various low tubal-rank tensor recovery tasks. However, these models usually require smooth change of data along the third dimension to ensure their low rank structures. In this paper, we propose a new definition of tensor rank named \textit{tensor Q-rank} by a column orthonormal matrix $\mathbf{Q}$, and further make $\mathbf{Q}$ data-dependent. With $\mathbf{Q}$ satisfying our orthogonal proximal constraint, the data tensor may have a more significant low tensor Q-rank structure than that of low tubal-rank structure. We also provide a corresponding envelope of our rank function and apply it to the low rank tensor completion problem. Then we give an effective algorithm and briefly analyze why our method works better than TNN based methods in the case of complex data with low sampling rate. Finally, experimental results on real-world datasets demonstrate the superiority of our proposed model in the tensor completion problem.

Multidimensional data have become ubiquitous and are frequently involved in situations where the information is aggregated over multiple data atoms. The aggregation can be over time or other features, such as geographical location or group affiliation. We often have access to multiple aggregated views of the same data, each aggregated in one or more dimensions, especially when data are collected or measured by different agencies. However, data mining and machine learning models require detailed data for personalized analysis and prediction. Thus, data disaggregation algorithms are becoming increasingly important in various domains. The goal of this paper is to reconstruct finer-scale data from multiple coarse views, aggregated over different (subsets of) dimensions. The proposed method, called PREMA, leverages low-rank tensor factorization tools to provide recovery guarantees under certain conditions. PREMA is flexible in the sense that it can perform disaggregation on data that have missing entries, i.e., partially observed. The proposed method considers challenging scenarios: i) the available views of the data are aggregated in two dimensions, i.e., double aggregation, and ii) the aggregation patterns are unknown. Experiments on real data from different domains, i.e., sales data from retail companies, crime counts, and weather observations, are presented to showcase the effectiveness of PREMA.

A multi-layer deep Gaussian process (DGP) model is a hierarchical composition of GP models with a greater expressive power. Exact DGP inference is intractable, which has motivated the recent development of deterministic and stochastic approximation methods. Unfortunately, the deterministic approximation methods yield a biased posterior belief while the stochastic one is computationally costly. This paper presents an implicit posterior variational inference (IPVI) framework for DGPs that can ideally recover an unbiased posterior belief and still preserve time efficiency. Inspired by generative adversarial networks, our IPVI framework achieves this by casting the DGP inference problem as a two-player game in which a Nash equilibrium, interestingly, coincides with an unbiased posterior belief. This consequently inspires us to devise a best-response dynamics algorithm to search for a Nash equilibrium (i.e., an unbiased posterior belief). Empirical evaluation shows that IPVI outperforms the state-of-the-art approximation methods for DGPs.

Expressiveness of deep models was recently addressed via the connection between neural networks (NNs) and kernel learning, where first-order dynamics of NN during a gradient-descent (GD) optimization were related to gradient similarity kernel, also known as Neural Tangent Kernel (NTK). In the majority of works this kernel is considered to be time-invariant, with its properties being defined entirely by NN architecture and independent of the learning task at hand. In contrast, in this paper we empirically explore these properties along the optimization and show that in practical applications the NN kernel changes in a very dramatic and meaningful way, with its top eigenfunctions aligning toward the target function learned by NN. Moreover, these top eigenfunctions serve sort of basis functions for NN output - a function represented by NN is spanned almost completely by them for the entire optimization process. Further, since the learning along top eigenfunctions is typically fast, their alignment with the target function improves the overall optimization performance. In addition, we study how the neural spectrum is affected by learning rate decay, typically done by practitioners, showing various trends in the kernel behavior. We argue that the presented phenomena may lead to a more complete theoretical understanding behind NN learning.

Assessing reliably the confidence of a deep neural network and predicting its failures is of primary importance for the practical deployment of these models. In this paper, we propose a new target criterion for model confidence, corresponding to the True Class Probability (TCP). We show how using the TCP is more suited than relying on the classic Maximum Class Probability (MCP). We provide in addition theoretical guarantees for TCP in the context of failure prediction. Since the true class is by essence unknown at test time, we propose to learn TCP criterion on the training set, introducing a specific learning scheme adapted to this context. Extensive experiments are conducted for validating the relevance of the proposed approach. We study various network architectures, small and large scale datasets for image classification and semantic segmentation. We show that our approach consistently outperforms several strong methods, from MCP to Bayesian uncertainty, as well as recent approaches specifically designed for failure prediction.

Learning from demonstrations is a popular tool for accelerating and reducing the exploration requirements of reinforcement learning. When providing expert demonstrations to human students, we know that the demonstrations must fall within a particular range of difficulties called the "Zone of Proximal Development (ZPD)". If they are too easy the student learns nothing, but if they are too difficult the student is unable to follow along. This raises the question: Given a set of potential demonstrators, which among them is best suited for teaching any particular learner? Prior work, such as the popular Deep Q-learning from Demonstrations (DQfD) algorithm has generally focused on single demonstrators. In this work we consider the problem of choosing among multiple demonstrators of varying skill levels. Our results align with intuition from human learners: it is not always the best policy to draw demonstrations from the best performing demonstrator (in terms of reward). We show that careful selection of teaching strategies can result in sample efficiency gains in the learner's environment across nine Atari games

User knowledge modeling systems are used as the most effective technology for grabbing new user's attention. Moreover, the quality of service (QOS) is increased by these intelligent services. This paper proposes two user knowledge classifiers based on artificial neural networks used as one of the influential parts of knowledge modeling systems. We employed multi-layer perceptron (MLP) and adaptive neural fuzzy inference system (ANFIS) as the classifiers. Moreover, we used real data contains the user's degree of study time, repetition number, their performance in exam, as well as the learning percentage, as our classifier's inputs. Compared with well-known methods like KNN and Bayesian classifiers used in other research with the same data sets, our experiments present better performance. Although, the number of samples in the train set is not large enough, the performance of the neuro-fuzzy classifier in the test set is 98.6% which is the best result in comparison with others. However, the comparison of MLP toward the ANFIS results presents performance reduction, although the MLP performance is more efficient than other methods like Bayesian and KNN. As our goal is evaluating and reporting the efficiency of a neuro-fuzzy classifier for user knowledge modeling systems, we utilized many different evaluation metrics such as Receiver Operating Characteristic and the Area Under its Curve, Total Accuracy, and Kappa statistics.