HIV RNA viral load (VL) is an important outcome variable in studies of HIV infected persons. There exists only a handful of methods which classify patients by viral load patterns. Most methods place limits on the use of viral load measurements, are often specific to a particular study design, and do not account for complex, temporal variation. To address this issue, we propose a set of four unambiguous computable characteristics (features) of time-varying HIV viral load patterns, along with a novel centroid-based classification algorithm, which we use to classify a population of 1,576 HIV positive clinic patients into one of five different viral load patterns (clusters) often found in the literature: durably suppressed viral load (DSVL), sustained low viral load (SLVL), sustained high viral load (SHVL), high viral load suppression (HVLS), and rebounding viral load (RVL). The centroid algorithm summarizes these clusters in terms of their centroids and radii. We show that this allows new viral load patterns to be assigned pattern membership based on the distance from the centroid relative to its radius, which we term radial normalization classification. This method has the benefit of providing an objective and quantitative method to assign viral load pattern membership with a concise and interpretable model that aids clinical decision making. This method also facilitates meta-analyses by providing computably distinct HIV categories. Finally we propose that this novel centroid algorithm could also be useful in the areas of cluster comparison for outcomes research and data reduction in machine learning.

In this study, we propose the integration of competitive learning into convolutional neural networks (CNNs) to improve the representation learning and efficiency of fine-tuning. Conventional CNNs use back propagation learning, and it enables powerful representation learning by a discrimination task. However, it requires huge amount of labeled data, and acquisition of labeled data is much harder than that of unlabeled data. Thus, efficient use of unlabeled data is getting crucial for DNNs. To address the problem, we introduce unsupervised competitive learning into the convolutional layer, and utilize unlabeled data for effective representation learning. The results of validation experiments using a toy model demonstrated that strong representation learning effectively extracted bases of images into convolutional filters using unlabeled data, and accelerated the speed of the fine-tuning of subsequent supervised back propagation learning. The leverage was more apparent when the number of filters was sufficiently large, and, in such a case, the error rate steeply decreased in the initial phase of fine-tuning. Thus, the proposed method enlarged the number of filters in CNNs, and enabled a more detailed and generalized representation. It could provide a possibility of not only deep but broad neural networks.

For better classification generative models are used to initialize the model and model features before training a classifier. Typically it is needed to solve separate unsupervised and supervised learning problems. Generative restricted Boltzmann machines and deep belief networks are widely used for unsupervised learning. We developed several supervised models based on DBN in order to improve this two-phase strategy. Modifying the loss function to account for expectation with respect to the underlying generative model, introducing weight bounds, and multi-level programming are applied in model development. The proposed models capture both unsupervised and supervised objectives effectively. The computational study verifies that our models perform better than the two-phase training approach.

In applications of machine learning to particle physics, a persistent challenge is how to go beyond discrimination to learn about the underlying physics. To this end, a powerful tool would be a framework for unsupervised learning, where the machine learns the intricate high-dimensional contours of the data upon which it is trained, without reference to pre-established labels. In order to approach such a complex task, an unsupervised network must be structured intelligently, based on a qualitative understanding of the data. In this paper, we scaffold the neural network's architecture around a leading-order model of the physics underlying the data. In addition to making unsupervised learning tractable, this design actually alleviates existing tensions between performance and interpretability. We call the framework JUNIPR: "Jets from UNsupervised Interpretable PRobabilistic models". In this approach, the set of particle momenta composing a jet are clustered into a binary tree that the neural network examines sequentially. Training is unsupervised and unrestricted: the network could decide that the data bears little correspondence to the chosen tree structure. However, when there is a correspondence, the network's output along the tree has a direct physical interpretation. JUNIPR models can perform discrimination tasks, through the statistically optimal likelihood-ratio test, and they permit visualizations of discrimination power at each branching in a jet's tree. Additionally, JUNIPR models provide a probability distribution from which events can be drawn, providing a data-driven Monte Carlo generator. As a third application, JUNIPR models can reweight events from one (e.g. simulated) data set to agree with distributions from another (e.g. experimental) data set.

Novel neural models have been proposed in recent years for learning under domain shift. Most models, however, only evaluate on a single task, on proprietary datasets, or compare to weak baselines, which makes comparison of models difficult. In this paper, we re-evaluate classic general-purpose bootstrapping approaches in the context of neural networks under domain shifts vs. recent neural approaches and propose a novel multi-task tri-training method that reduces the time and space complexity of classic tri-training. Extensive experiments on two benchmarks are negative: while our novel method establishes a new state-of-the-art for sentiment analysis, it does not fare consistently the best. More importantly, we arrive at the somewhat surprising conclusion that classic tri-training, with some additions, outperforms the state of the art. We conclude that classic approaches constitute an important and strong baseline.

Convolutional Neural Networks (CNN's) are restricted by their massive computation and high storage. Parameter pruning is a promising approach for CNN compression and acceleration, which aims at eliminating redundant model parameters with tolerable performance loss. Despite its effectiveness, existing regularization-based parameter pruning methods usually assign a fixed regularization parameter to all weights, which neglects the fact that different weights may have different importance to CNN. To solve this problem, we propose a theoretically sound regularization-based pruning method to incrementally assign different regularization parameters to different weights based on their importance to the network. On AlexNet and VGG-16, our method can achieve 4x theoretical speedup with similar accuracies compared with the baselines. For ResNet-50, the proposed method also achieves 2x acceleration and only suffers 0.1% top-5 accuracy loss.

Learning the disentangled representation of interpretable generative factors of data is one of the foundations to allow artificial intelligence to think like people. In this paper, we propose the analogical training strategy for the unsupervised disentangled representation learning in generative models. The analogy is one of the typical cognitive processes, and our proposed strategy is based on the observation that sample pairs in which one is different from the other in one specific generative factor show the same analogical relation. Thus, the generator is trained to generate sample pairs from which a designed classifier can identify the underlying analogical relation. In addition, we propose a disentanglement metric called the subspace score, which is inspired by subspace learning methods and does not require supervised information. Experiments show that our proposed training strategy allows the generative models to find the disentangled factors, and that our methods can give competitive performances as compared with the state-of-the-art methods.

The past year has witnessed rapid advances in sequence-to-sequence (seq2seq) modeling for Machine Translation (MT). The classic RNN-based approaches to MT were first out-performed by the convolutional seq2seq model, which was then out-performed by the more recent Transformer model. Each of these new approaches consists of a fundamental architecture accompanied by a set of modeling and training techniques that are in principle applicable to other seq2seq architectures. In this paper, we tease apart the new architectures and their accompanying techniques in two ways. First, we identify several key modeling and training techniques, and apply them to the RNN architecture, yielding a new RNMT+ model that outperforms all of the three fundamental architectures on the benchmark WMT'14 English to French and English to German tasks. Second, we analyze the properties of each fundamental seq2seq architecture and devise new hybrid architectures intended to combine their strengths. Our hybrid models obtain further improvements, outperforming the RNMT+ model on both benchmark datasets.

Novel view synthesis is an important problem in computer vision and graphics. Over the years a large number of solutions have been put forward to solve the problem. However, the large-baseline novel view synthesis problem is far from being "solved". Recent works have attempted to use Convolutional Neural Networks (CNNs) to solve view synthesis tasks. Due to the difficulty of learning scene geometry and interpreting camera motion, CNNs are often unable to generate realistic novel views. In this paper, we present a novel view synthesis approach based on stereo-vision and CNNs that decomposes the problem into two sub-tasks: view dependent geometry estimation and texture inpainting. Both tasks are structured prediction problems that could be effectively learned with CNNs. Experiments on the KITTI Odometry dataset show that our approach is more accurate and significantly faster than the current state-of-the-art. The code and supplementary material will be publicly available. Results could be found here https://youtu.be/5pzS9jc-5t0.

Peer reviewing is a central component in the scientific publishing process. We present the first public dataset of scientific peer reviews available for research purposes (PeerRead v1) providing an opportunity to study this important artifact. The dataset consists of 14.7K paper drafts and the corresponding accept/reject decisions in top-tier venues including ACL, NIPS and ICLR. The dataset also includes 10.7K textual peer reviews written by experts for a subset of the papers. We describe the data collection process and report interesting observed phenomena in the peer reviews. We also propose two novel NLP tasks based on this dataset and provide simple baseline models. In the first task, we show that simple models can predict whether a paper is accepted with up to 21% error reduction compared to the majority baseline. In the second task, we predict the numerical scores of review aspects and show that simple models can outperform the mean baseline for aspects with high variance such as 'originality' and 'impact'.