In this paper, we propose a general model for plane-based clustering. The general model contains many existing plane-based clustering methods, e.g., k-plane clustering (kPC), proximal plane clustering (PPC), twin support vector clustering (TWSVC) and its extensions. Under this general model, one may obtain an appropriate clustering method for specific purpose. The general model is a procedure corresponding to an optimization problem, where the optimization problem minimizes the total loss of the samples. Thereinto, the loss of a sample derives from both within-cluster and between-cluster. In theory, the termination conditions are discussed, and we prove that the general model terminates in a finite number of steps at a local or weak local optimal point. Furthermore, based on this general model, we propose a plane-based clustering method by introducing a new loss function to capture the data distribution precisely. Experimental results on artificial and public available datasets verify the effectiveness of the proposed method.

Deep learning has been successfully applied to a variety of image classification tasks. There has been keen interest to apply deep learning in the medical domain, particularly specialties that heavily utilize imaging, such as ophthalmology. One issue that may hinder application of deep learning to the medical domain is the vast amount of data necessary to train deep neural networks (DNNs). Because of regulatory and privacy issues associated with medicine, and the generally proprietary nature of data in medical domains, obtaining large datasets to train DNNs is a challenge, particularly in the ophthalmology domain. Transfer learning is a technique developed to address the issue of applying DNNs for domains with limited data. Prior reports on transfer learning have examined custom networks to fully train or used a particular DNN for transfer learning. However, to the best of my knowledge, no work has systematically examined a suite of DNNs for transfer learning for classification of diabetic retinopathy, diabetic macular edema, and two key features of age-related macular degeneration. This work attempts to investigate transfer learning for classification of these ophthalmic conditions. Part I gives a condensed overview of neural networks and the DNNs under evaluation. Part II gives the reader the necessary background concerning diabetic retinopathy and prior work on classification using retinal fundus photographs. The methodology and results of transfer learning for diabetic retinopathy classification are presented, showing that transfer learning towards this domain is feasible, with promising accuracy. Part III gives an overview of diabetic macular edema, choroidal neovascularization and drusen (features associated with age-related macular degeneration), and presents results for transfer learning evaluation using optical coherence tomography to classify these entities.

Neural networks play an increasingly important role in the field of machine learning and are included in many applications in society. Unfortunately, neural networks suffer from adversarial samples generated to attack them. However, most of the generation approaches either assume that the attacker has full knowledge of the neural network model or are limited by the type of attacked model. In this paper, we propose a new approach that generates a black-box attack to neural networks based on the swarm evolutionary algorithm. Benefiting from the improvements in the technology and theoretical characteristics of evolutionary algorithms, our approach has the advantages of effectiveness, black-box attack, generality, and randomness. Our experimental results show that both the MNIST images and the CIFAR-10 images can be perturbed to successful generate a black-box attack with 100\% probability on average. In addition, the proposed attack, which is successful on distilled neural networks with almost 100\% probability, is resistant to defensive distillation. The experimental results also indicate that the robustness of the artificial intelligence algorithm is related to the complexity of the model and the data set. In addition, we find that the adversarial samples to some extent reproduce the characteristics of the sample data learned by the neural network model.

This paper aims to provide a better understanding of a symmetric loss. First, we show that using a symmetric loss is advantageous in the balanced error rate (BER) minimization and area under the receiver operating characteristic curve (AUC) maximization from corrupted labels. Second, we prove general theoretical properties of symmetric losses, including a classification-calibration condition, excess risk bound, conditional risk minimizer, and AUC-consistency condition. Third, since all nonnegative symmetric losses are non-convex, we propose a convex barrier hinge loss that benefits significantly from the symmetric condition, although it is not symmetric everywhere. Finally, we conduct experiments on BER and AUC optimization from corrupted labels to validate the relevance of the symmetric condition.

Anomaly detecting as an important technical in cloud computing is applied to support smooth running of the cloud platform. Traditional detecting methods based on statistic, analysis, etc. lead to the high false-alarm rate due to non-adaptive and sensitive parameters setting. We presented an online model for anomaly detecting using machine learning theory. However, most existing methods based on machine learning linked all features from difference sub-systems into a long feature vector directly, which is difficult to both exploit the complement information between sub-systems and ignore multi-view features enhancing the classification performance. Aiming to this problem, the proposed method automatic fuses multi-view features and optimize the discriminative model to enhance the accuracy. This model takes advantage of extreme learning machine (ELM) to improve detection efficiency. ELM is the single hidden layer neural network, which is transforming iterative solution the output weights to solution of linear equations and avoiding the local optimal solution. Moreover, we rank anomies according to the relationship between samples and the classification boundary, and then assigning weights for ranked anomalies, retraining the classification model finally. Our method exploits the complement information between sub-systems sufficiently, and avoids the influence from imbalance dataset, therefore, deal with various challenges from the cloud computing platform. We deploy the privately cloud platform by Openstack, verifying the proposed model and comparing results to the state-of-the-art methods with better efficiency and simplicity.

Softmax is a standard final layer used in Neural Nets (NNs) to summarize information encoded in the trained NN and return a prediction. However, Softmax leverages only a subset of the class-specific structure encoded in the trained model and ignores potentially valuable information: During training, models encode an array $D$ of class response distributions, where $D_{ij}$ is the distribution of the $j^{th}$ pre-Softmax readout neuron's responses to the $i^{th}$ class. Given a test sample, Softmax implicitly uses only the row of this array $D$ that corresponds to the readout neurons' responses to the sample's true class. Leveraging more of this array $D$ can improve classifier accuracy, because the likelihoods of two competing classes can be encoded in other rows of $D$. To explore this potential resource, we develop a hybrid classifier (Softmax-Pooling Hybrid, $SPH$) that uses Softmax on high-scoring samples, but on low-scoring samples uses a log-likelihood method that pools the information from the full array $D$. We apply $SPH$ to models trained on a vectorized MNIST dataset to varying levels of accuracy. $SPH$ replaces only the final Softmax layer in the trained NN, at test time only. All training is the same as for Softmax. Because the pooling classifier performs better than Softmax on low-scoring samples, $SPH$ reduces test set error by 6% to 23%, using the exact same trained model, whatever the baseline Softmax accuracy. This reduction in error reflects hidden capacity of the trained NN that is left unused by Softmax.

Autonomous driving is getting a lot of attention in the last decade and will be the hot topic at least until the first successful certification of a car with Level 5 autonomy. There are many public datasets in the academic community. However, they are far away from what a robust industrial production system needs. There is a large gap between academic and industrial setting and a substantial way from a research prototype, built on public datasets, to a deployable solution which is a challenging task. In this paper, we focus on bad practices that often happen in the autonomous driving from an industrial deployment perspective. Data design deserves at least the same amount of attention as the model design. There is very little attention paid to these issues in the scientific community, and we hope this paper encourages better formalization of dataset design. More specifically, we focus on the datasets design and validation scheme for autonomous driving, where we would like to highlight the common problems, wrong assumptions, and steps towards avoiding them, as well as some open problems.

Training very large machine learning models requires a distributed computing approach, with communication of the model updates often being the bottleneck. For this reason, several methods based on the compression (e.g., sparsification and/or quantization) of the updates were recently proposed, including QSGD (Alistarh et al., 2017), TernGrad (Wen et al., 2017), SignSGD (Bernstein et al., 2018), and DQGD (Khirirat et al., 2018). However, none of these methods are able to learn the gradients, which means that they necessarily suffer from several issues, such as the inability to converge to the true optimum in the batch mode, inability to work with a nonsmooth regularizer, and slow convergence rates. In this work we propose a new distributed learning method---DIANA---which resolves these issues via compression of gradient differences. We perform a theoretical analysis in the strongly convex and nonconvex settings and show that our rates are vastly superior to existing rates. Our analysis of block-quantization and differences between $\ell_2$ and $\ell_\infty$ quantization closes the gaps in theory and practice. Finally, by applying our analysis technique to TernGrad, we establish the first convergence rate for this method.

Toxicity prediction of chemical compounds is a grand challenge. Lately, it achieved significant progress in accuracy but using a huge set of features, implementing a complex blackbox technique such as a deep neural network, and exploiting enormous computational resources. In this paper, we strongly argue for the models and methods that are simple in machine learning characteristics, efficient in computing resource usage, and powerful to achieve very high accuracy levels. To demonstrate this, we develop a single task-based chemical toxicity prediction framework using only 2D features that are less compute intensive. We effectively use a decision tree to obtain an optimum number of features from a collection of thousands of them. We use a shallow neural network and jointly optimize it with decision tree taking both network parameters and input features into account. Our model needs only a minute on a single CPU for its training while existing methods using deep neural networks need about 10 min on NVidia Tesla K40 GPU. However, we obtain similar or better performance on several toxicity benchmark tasks. We also develop a cumulative feature ranking method which enables us to identify features that can help chemists perform prescreening of toxic compounds effectively.

Humans are capable of attributing latent mental contents such as beliefs, or intentions to others. The social skill is critical in everyday life to reason about the potential consequences of their behaviors so as to plan ahead. It is known that humans use this reasoning ability recursively, i.e. considering what others believe about their own beliefs. In this paper, we start from level-$1$ recursion and introduce a probabilistic recursive reasoning (PR2) framework for multi-agent reinforcement learning. Our hypothesis is that it is beneficial for each agent to account for how the opponents would react to its future behaviors. Under the PR2 framework, we adopt variational Bayes methods to approximate the opponents' conditional policy, to which each agent finds the best response and then improve their own policy. We develop decentralized-training-decentralized-execution algorithms, PR2-Q and PR2-Actor-Critic, that are proved to converge in the self-play scenario when there is one Nash equilibrium. Our methods are tested on both the matrix game and the differential game, which have a non-trivial equilibrium where common gradient-based methods fail to converge. Our experiments show that it is critical to reason about how the opponents believe about what the agent believes. We expect our work to contribute a new idea of modeling the opponents to the multi-agent reinforcement learning community.