Deep learning models for survival analysis have gained significant attention in the literature, but they suffer from severe performance deficits when the dataset contains many irrelevant features. We give empirical evidence for this problem in real-world medical settings using the state-of-the-art model DeepHit. Furthermore, we develop methods to improve the deep learning model through novel approaches to feature selection in survival analysis. We propose filter methods for hard feature selection and a neural network architecture that weights features for soft feature selection. Our experiments on two real-world medical datasets demonstrate that substantial performance improvements against the original models are achievable.

Segmentation of magnetic resonance (MR) images is a fundamental step in many medical imaging-based applications. The recent implementation of deep convolutional neural networks (CNNs) in image processing has been shown to have significant impacts on medical image segmentation. Network training of segmentation CNNs typically requires images and paired annotation data representing pixel-wise tissue labels referred to as masks. However, the supervised training of highly efficient CNNs with deeper structure and more network parameters requires a large number of training images and paired tissue masks. Thus, there is great need to develop a generalized CNN-based segmentation method which would be applicable for a wide variety of MR image datasets with different tissue contrasts. The purpose of this study was to develop and evaluate a generalized CNN-based method for fully-automated segmentation of different MR image datasets using a single set of annotated training data. A technique called cycle-consistent generative adversarial network (CycleGAN) is applied as the core of the proposed method to perform image-to-image translation between MR image datasets with different tissue contrasts. A joint segmentation network is incorporated into the adversarial network to obtain additional segmentation functionality. The proposed method was evaluated for segmenting bone and cartilage on two clinical knee MR image datasets acquired at our institution using only a single set of annotated data from a publicly available knee MR image dataset. The new technique may further improve the applicability and efficiency of CNN-based segmentation of medical images while eliminating the need for large amounts of annotated training data.

Automated detection of voice disorders with computational methods is a recent research area in the medical domain since it requires a rigorous endoscopy for the accurate diagnosis. Efficient screening methods are required for the diagnosis of voice disorders so as to provide timely medical facilities in minimal resources. Detecting Voice disorder using computational methods is a challenging problem since audio data is continuous due to which extracting relevant features and applying machine learning is hard and unreliable. This paper proposes a Long short term memory model (LSTM) to detect pathological voice disorders and evaluates its performance in a real 400 testing samples without any labels. Different feature extraction methods are used to provide the best set of features before applying LSTM model for classification. The paper describes the approach and experiments that show promising results with 22% sensitivity, 97% specificity and 56% unweighted average recall.

Much of machine learning research focuses on producing models which perform well on benchmark tasks, in turn improving our understanding of the challenges associated with those tasks. From the perspective of ML researchers, the content of the task itself is largely irrelevant, and thus there have increasingly been calls for benchmark tasks to more heavily focus on problems which are of social or cultural relevance. In this work, we introduce Kuzushiji-MNIST, a dataset which focuses on Kuzushiji (cursive Japanese), as well as two larger, more challenging datasets, Kuzushiji-49 and Kuzushiji-Kanji. Through these datasets, we wish to engage the machine learning community into the world of classical Japanese literature.

FRAME (Filters, Random fields, And Maximum Entropy) is an energy-based descriptive model that synthesizes visual realism by capturing mutual patterns from structural input signals. The maximum likelihood estimation (MLE) is applied by default, yet conventionally causes the unstable training energy that wrecks the generated structures, which remains unexplained. In this paper, we provide a new theoretical insight to analyze FRAME, from a perspective of particle physics ascribing the weird phenomenon to KL-vanishing issue. In order to stabilize the energy dissipation, we propose an alternative Wasserstein distance in discrete time based on the conclusion that the Jordan-Kinderlehrer-Otto (JKO) discrete flow approximates KL discrete flow when the time step size tends to 0. Besides, this metric can still maintain the model's statistical consistency. Quantitative and qualitative experiments have been respectively conducted on several widely used datasets. The empirical studies have evidenced the effectiveness and superiority of our method.

A model of music needs to have the ability to recall past details and have a clear, coherent understanding of musical structure. Detailed in the paper is a deep reinforcement learning architecture that predicts and generates polyphonic music aligned with musical rules. The probabilistic model presented is a Bi-axial LSTM trained with a pseudo-kernel reminiscent of a convolutional kernel. To encourage exploration and impose greater global coherence on the generated music, a deep reinforcement learning approach DQN is adopted. When analyzed quantitatively and qualitatively, this approach performs well in composing polyphonic music.

Federated learning has become an exciting direction for both research and practical training of models with user data. Although data remains decentralized in federated learning, it is common to assume that the model updates are sent in the clear from the devices to the server. Differential privacy has been proposed as a way to ensure the model remains private, but this does not address the issue that model updates can be seen on the server, and lead to leakage of user data. Local differential privacy is one of the strongest forms of privacy protection so that each individual's data is privatized. However, local differential privacy, as it is traditionally used, may prove to be too stringent of a privacy condition in many high dimensional problems, such as in distributed model fitting. We propose a new paradigm for local differential privacy by providing protections against certain adversaries. Specifically, we ensure that adversaries with limited prior information cannot reconstruct, with high probability, the original data within some prescribed tolerance. This interpretation allows us to consider larger privacy parameters. We then design (optimal) DP mechanisms in this large privacy parameter regime. In this work, we combine local privacy protections along with central differential privacy to present a practical approach to do model training privately. Further, we show that these privacy restrictions maintain utility in image classification and language models that is comparable to federated learning without these privacy restrictions.

Abstract--Deep neural networks are susceptible to various inference attacks as they remember information about their training data. We perform a comprehensive analysis of white-box privacy inference attacks on deep learning models. We measure the privacy leakage by leveraging the final model parameters as well as the parameter updates during the training and finetuning processes.We design the attacks in the stand-alone and federated settings, with respect to passive and active inference attackers, and assuming different adversary prior knowledge. We evaluate our novel white-box membership inference attacks against deep learning algorithms to measure their training data membership leakage. We show that a straightforward extension of the known black-box attacks to the white-box setting (through analyzing the outputs of activation functions) is ineffective. We therefore design new algorithms tailored to the white-box setting by exploiting the privacy vulnerabilities of the stochastic gradient descent algorithm, widely used to train deep neural networks. We show that even well-generalized models are significantly susceptible towhite-box membership inference attacks, by analyzing state-of-the-art pre-trained and publicly available models for the CIFAR dataset. We also show how adversarial participants of a federated learning setting can run active membership inference attacks against other participants, even when the global model achieves high prediction accuracies. I. INTRODUCTION Machine learning models based on deep neural networks have been shown to have significantly high generalization accuracies for various learning tasks, from image and speech recognition to generating realistic-looking data. This success has led to many applications and services that use deep learning algorithms on large-dimension (and potentially sensitive) userdata, including user speeches, images, and medical, financial, social, and location data points. The crucial question we ask in this paper is the following: How much is the privacy risks of deep learning for individuals whose data is used as part of the training set? In other words, how much is the information leakage of deep learning algorithms about their individual training data samples? We define privacy-sensitive leakage of a model about a set of target trained data record(s) as the information that an adversary can infer about the data records, that could not have been inferred from similar models not using the target data records. This distinguishes between the information that we can learn from the model about the population and the information that it leaks about particular samples from the population that were in its training set. The former indicates utility gain, and the later reflects privacy loss. We design inference attacks to quantify such privacy leakage. Theinference attacks fall into two fundamental and related categories: tracing (a.k.a.

Accurate classification of self-care problems in children who suffer from physical and motor affliction is an important problem in the healthcare industry. This is a difficult and a time consumming process and it needs the expertise of occupational therapists. In recent years, healthcare professionals have opened up to the idea of using expert systems and artificial intelligence in the diagnosis and classification of self care problems. In this study, we propose a new deep learning based approach named Care2Vec for solving these kind of problems and use a real world self care activities dataset that is based on a conceptual framework designed by the World Health Organization (WHO). Care2Vec is a mix of unsupervised and supervised learning where we use Autoencoders and Deep neural networks as a two step modeling process. We found that Care2Vec has a better prediction accuracy than some of the traditional methods reported in the literature for solving the self care classification problem viz. Decision trees and Artificial neural networks.

Abstract--In this paper, a detailed study on crime classification and prediction using deep learning architectures is presented. We examine the effectiveness of deep learning algorithms on this domain and provide recommendations for designing and training deep learning systems for predicting crime areas, using open data from police reports. Having as training data time-series of crime types per location, a comparative study of 10 state-of-the-art methods against 3 different deep learning configurations is conducted. In our experiments with five publicly available datasets, we demonstrate that the deep learning-based methods consistently outperform the existing best-performing methods. Moreover, we evaluate the effectiveness of different parameters in the deep learning architectures and give insights for configuring them in order to achieve improved performance in crime classification and finally crime prediction. REDICTIVE policing is the use of analytical techniques to identify either likely places of future crime scenes or past crime perpetrators, by applying statistical predictions [29]. As a crime typically involves a perpetrator and a target and occurs at a certain place and time, techniques of predictive policing need to answer: a) who will commit a crime, b) who will be offended, c) what type of crime, d) in which location and e) at what time a new crime will take place. This work does not focus on the victim and the offender, but on the prediction of occurrence of a certain crime type per location and time using past data. The ultimate goal, in a policing context, is the selection of the top areas in the city for the prioritization of law enforcement resources per department. One of the most challenging issues of police departments is to have accurate crime forecasts to dynamically deploy patrols and other resources so as to improve deterring of crime occurrence and police response times. Routine activity theory [8] suggests that most crimes take place when three conditions are met: a motivated offender, a suitable victim and lack of victim protection. The rational choice theory [9], suggests that prospective criminal weights the gain of successfully committing the crime against the probability of being caught and makes a rational choice whether to actually commit the crime or not. Both theories agree that a crime takes place when a person willing to commit it has an opportunity to do so. Daras are with the Information Technologies Institute, Centre for Research and Technology Hellas, Thessaloniki, Greece.