Cancer is a complex disease, the understanding and treatment of which are being aided through increases in the volume of collected data and in the scale of deployed computing power. Consequently, there is a growing need for the development of data-driven and, in particular, deep learning methods for various tasks such as cancer diagnosis, detection, prognosis, and prediction. Despite recent successes, however, designing high-performing deep learning models for nonimage and nontext cancer data is a time-consuming, trial-and-error, manual task that requires both cancer domain and deep learning expertise. To that end, we develop a reinforcement-learning-based neural architecture search to automate deep-learning-based predictive model development for a class of representative cancer data. We develop custom building blocks that allow domain experts to incorporate the cancer-data-specific characteristics. We show that our approach discovers deep neural network architectures that have significantly fewer trainable parameters, shorter training time, and accuracy similar to or higher than those of manually designed architectures. We study and demonstrate the scalability of our approach on up to 1,024 Intel Knights Landing nodes of the Theta supercomputer at the Argonne Leadership Computing Facility.

Designing reinforcement learning methods which find a good policy with as few samples as possible is a key goal of both empirical and theoretical research. On the theoretical side there are two main ways, regret- or PAC (probably approximately correct) bounds, to measure and guarantee sample-efficiency of a method. Ideally, we would like to have algorithms that have good performance according to both criteria, as they measure different aspects of sample efficiency and we have shown previously [1] that one cannot simply go from one to the other. In a specific setting called tabular episodic MDPs, a recent algorithm achieved close to optimal regret bounds [2] but there was no methods known to be close to optimal according to the PAC criterion despite a long line of research. In our work presented at ICML 2019, we close this gap with a new method that achieves minimax-optimal PAC (and regret) bounds which match the statistical worst-case lower bounds in the dominating terms.

"Artificial intelligence will reach human levels by around 2029. Follow that out further to, say, 2045, we will have multiplied the intelligence, the human biological machine intelligence of our civilization a billion-fold." Machine learning (ML) and artificial intelligence (AI) are ruling the digital world today. These technologies have the ability to completely transform the way a business operates. With the increasing adoption and business applications of AI and ML, many IT professionals are choosing AI and ML as their career.

Stochastic Gradient Langevin Dynamics, the "unadjusted Langevin algorithm", and Adaptive Langevin Dynamics (also known as Stochastic Gradient Nos\'{e}-Hoover dynamics) are examples of existing thermodynamic parameterization methods in use for machine learning, but these can be substantially improved. We find that by partitioning the parameters based on natural layer structure we obtain schemes with rapid convergence for data sets with complicated loss landscapes. We describe easy-to-implement hybrid partitioned numerical algorithms, based on discretized stochastic differential equations, which are adapted to feed-forward neural networks, including LaLa (a multi-layer Langevin algorithm), AdLaLa (combining the adaptive Langevin and Langevin algorithms) and LOL (combining Langevin and Overdamped Langevin); we examine the convergence of these methods using numerical studies and compare their performance among themselves and in relation to standard alternatives such as stochastic gradient descent and ADAM. We present evidence that thermodynamic parameterization methods can be (i) faster, (ii) more accurate, and (iii) more robust than standard algorithms incorporated into machine learning frameworks, in particular for data sets with complicated loss landscapes. Moreover, we show in numerical studies that methods based on sampling excite many degrees of freedom. The equipartition property, which is a consequence of their ergodicity, means that these methods keep in play an ensemble of low-loss states during the training process. By drawing parameter states from a sufficiently rich distribution of nearby candidate states, we show that the thermodynamic schemes produce smoother classifiers, improve generalization and reduce overfitting compared to traditional optimizers.

End-to-end text-to-speech (TTS) synthesis is a method that directly converts input text to output acoustic features using a single network. A recent advance of end-to-end TTS is due to a key technique called attention mechanisms, and all successful methods proposed so far have been based on soft attention mechanisms. However, although network structures are becoming increasingly complex, end-to-end TTS systems with soft attention mechanisms may still fail to learn and to predict accurate alignment between the input and output. This may be because the soft attention mechanisms are too flexible. Therefore, we propose an approach that has more explicit but natural constraints suitable for speech signals to make alignment learning and prediction of end-to-end TTS systems more robust. The proposed system, with the constrained alignment scheme borrowed from segment-to-segment neural transduction (SSNT), directly calculates the joint probability of acoustic features and alignment given an input text. The alignment is designed to be hard and monotonically increase by considering the speech nature, and it is treated as a latent variable and marginalized during training. During prediction, both the alignment and acoustic features can be generated from the probabilistic distributions. The advantages of our approach are that we can simplify many modules for the soft attention and that we can train the end-to-end TTS model using a single likelihood function. As far as we know, our approach is the first end-to-end TTS without a soft attention mechanism.

Preprint submitted to RGN Publications on 21 /5/2018 Abstract The credit cards' fraud transactions detection is the important problem in machine learning field. To detect the credit cards' fraud transactions help reduce the significant loss of the credit cards' holders and the banks. To detect the credit cards' fraud transactions, data scientists normally employ the un - supervised learning techniques and supervised learning technique. In this paper, we employ the graph p - Laplacian based semi - supervised learning methods combi ned with the under - sampling technique such as Cluster Centroids to solve the credit cards' fraud transactions detection problem. Experimental results show that that the graph p - Laplacian semi - supervised learning method s outper form the current state of art graph Laplacian based semi - supervised learning method ( p 2). 2010 AMS Classi fi cation: 05C85 Keywords and phrases: graph p - Laplacian, credit card, fraud detection, semi - supervised learning Article type: Research article 1 Introduction While purchasing online, the transactions can be done by using credit cards that are issued by the bank.

We present a queuing model of parking dynamics and a model-based prediction method to provide real-time probabilistic forecasts of future parking occupancy. The queuing model has a non-homogeneous arrival rate and time-varying service time distribution. All statistical assumptions of the model are verified using data from 29 truck parking locations, each with between 55 and 299 parking spots. For each location and each spot the data specifies the arrival and departure times of a truck, for 16 months of operation. The modeling framework presented in this paper provides empirical support for queuing models adopted in many theoretical studies and policy designs. We discuss how our framework can be used to study parking problems in different environments. Based on the queuing model, we propose two prediction methods, a microscopic method and a macroscopic method, that provide a real-time probabilistic forecast of parking occupancy for an arbitrary forecast horizon. These model-based methods convert a probabilistic forecast problem into a parameter estimation problem that can be tackled using classical estimation methods such as regressions or pure machine learning algorithms. We characterize a lower bound for an arbitrary real-time prediction algorithm. We evaluate the performance of these methods using the truck data comparing the outcomes of their implementations with other model-based and model-free methods proposed in the literature.

This paper presents an unsupervised method that trains neural source separation by using only multichannel mixture signals. Conventional neural separation methods require a lot of supervised data to achieve excellent performance. Although multichannel methods based on spatial information can work without such training data, they are often sensitive to parameter initialization and degraded with the sources located close to each other. The proposed method uses a cost function based on a spatial model called a complex Gaussian mixture model (cGMM). This model has the time-frequency (TF) masks and direction of arrivals (DoAs) of sources as latent variables and is used for training separation and localization networks that respectively estimate these variables. This joint training solves the frequency permutation ambiguity of the spatial model in a unified deep Bayesian framework. In addition, the pre-trained network can be used not only for conducting monaural separation but also for efficiently initializing a multichannel separation algorithm. Experimental results with simulated speech mixtures showed that our method outperformed a conventional initialization method.

We develop a three - step diversity ensemble creation algorithm: (1) Creating a pool of candidate ensemble member models, or so called base models; (2) Creating a pool of candidate ensemble teams with their diversity scores higher than the pre - defined minimum diversity threshold; and (3) Developing robust ensemble consensus methods, which can effectively combine, rank and integrate predictions from members of an ensemble committee to produce high accuracy ensemble prediction output again st adversarial examples. D ifferent ensemble creation methods tend to have varying level of diversity. A. Creating Ensemble s of Type 1 diversity We want to construct a pool of N redundant DNN models trained on the same learning task as the base classifiers. Preferably, the best ensemble committee members are those base classifiers that are relatively diverse and have high individual test accuracy. T he type 1 diversity ensemble creation algorithm requires that every base model in the pool meet s the type 1 dive rsity and ha s high benign test accuracy comparable to that of the target model under protection. One approach is to add one member model to the pool at a time. Assume that we initialize the pool with a privately trained DNN model. We only allow the next mo del to be added to the pool if it is trained independently using different hyper - parameters or different neural network structures or algorithms and it meet s the high benign test accuracy requirement.