Predicting how proteins interact with one another - that is, which surfaces of one protein bind to which surfaces of another protein - is a central problem in biology. Here we present Siamese Atomic Surfacelet Network (SASNet), the first end-to-end learning method for protein interface prediction. Despite using only spatial coordinates and identities of atoms as inputs, SASNet outperforms state-of-the-art methods that rely on complex, hand-selected features. These results are particularly striking because we train the method entirely on a significantly biased data set that does not account for the fact that proteins deform when binding to one another. Nonetheless, our network maintains high performance, without retraining, when tested on real cases in which proteins do deform. This suggests that it has learned fundamental properties of protein structure and dynamics, which has important implications for a variety of key problems related to biomolecular structure.

For a company looking to provide delightful user experiences, it is of paramount importance to take care of any customer issues. This paper proposes COTA, a system to improve speed and reliability of customer support for end users through automated ticket classification and answers selection for support representatives. Two machine learning and natural language processing techniques are demonstrated: one relying on feature engineering (COTA v1) and the other exploiting raw signals through deep learning architectures (COTA v2). COTA v1 employs a new approach that converts the multi-classification task into a ranking problem, demonstrating significantly better performance in the case of thousands of classes. For COTA v2, we propose an Encoder-Combiner-Decoder, a novel deep learning architecture that allows for heterogeneous input and output feature types and injection of prior knowledge through network architecture choices. This paper compares these models and their variants on the task of ticket classification and answer selection, showing model COTA v2 outperforms COTA v1, and analyzes their inner workings and shortcomings. Finally, an A/B test is conducted in a production setting validating the real-world impact of COTA in reducing issue resolution time by 10 percent without reducing customer satisfaction.

Why deep neural networks (DNNs) capable of overfitting often generalize well in practice is a mystery in deep learning. Existing works indicate that this observation holds for both complicated real datasets and simple datasets of one-dimensional (1-d) functions. In this work, for general low-frequency dominant 1-d functions, we find that a DNN with common settings first quickly captures the dominant low-frequency components, and then relatively slowly captures high-frequency ones. We call this phenomenon Frequency Principle (F-Principle). F-Principle can be observed over various DNN setups of different activation functions, layer structures and training algorithms in our experiments. F-Principle can be used to understand (i) the behavior of DNN training in the information plane and (ii) why DNNs often generalize well albeit its ability of overfitting. This F-Principle potentially can provide insights into understanding the general principle underlying DNN optimization and generalization for real datasets.

In this paper, we unravel a fundamental connection between weighted finite automata (WFAs) and second-order recurrent neural networks (2-RNNs): in the case of sequences of discrete symbols, WFAs and 2-RNNs with linear activation functions are expressively equivalent. Motivated by this result, we build upon a recent extension of the spectral learning algorithm to vector-valued WFAs and propose the first provable learning algorithm for linear 2-RNNs defined over sequences of continuous input vectors. This algorithm relies on estimating low rank sub-blocks of the so-called Hankel tensor, from which the parameters of a linear 2-RNN can be provably recovered. The performances of the proposed method are assessed in a simulation study.

A new whole-sentence language model - neural trans-dimensional random field language model (neural TRF LM), where sentences are modeled as a collection of random fields, and the potential function is defined by a neural network, has been introduced and successfully trained by noise-contrastive estimation (NCE). In this paper, we extend NCE and propose dynamic noise-contrastive estimation (DNCE) to solve the two problems observed in NCE training. First, a dynamic noise distribution is introduced and trained simultaneously to converge to the data distribution. This helps to significantly cut down the noise sample number used in NCE and reduce the training cost. Second, DNCE discriminates between sentences generated from the noise distribution and sentences generated from the interpolation of the data distribution and the noise distribution. This alleviates the overfitting problem caused by the sparseness of the training set. With DNCE, we can successfully and efficiently train neural TRF LMs on large corpus (about 0.8 billion words) with large vocabulary (about 568 K words). Neural TRF LMs perform as good as LSTM LMs with less parameters and being 5x~114x faster in rescoring sentences. Interpolating neural TRF LMs with LSTM LMs and n-gram LMs can further reduce the error rates.

Deep neural networks (DNNs) have been proven to have many redundancies. Hence, many efforts have been made to compress DNNs. However, the existing model compression methods treat all the input samples equally while ignoring the fact that the difficulties of various input samples being correctly classified are different. To address this problem, DNNs with adaptive dropping mechanism are well explored in this work. To inform the DNNs how difficult the input samples can be classified, a guideline that contains the information of input samples is introduced to improve the performance. Based on the developed guideline and adaptive dropping mechanism, an innovative soft-guided adaptively-dropped (SGAD) neural network is proposed in this paper. Compared with the 32 layers residual neural networks, the presented SGAD can reduce the FLOPs by 77% with less than 1% drop in accuracy on CIFAR-10.

ABSTRACT A deep recurrent neural network with audio input is applied to model basic dance steps. The proposed model employs multilayered Long Short-Term Memory (LSTM) layers and convolutional layers to process the audio power spectrum. This end-to-end approach has an auto-conditioned decode configuration that reduces accumulation of feedback error. Experimental results demonstrate that, after training using a small dataset, the model generates basic dance steps with low cross entropy and maintains a motion beat F-measure score similar to that of a baseline dancer. In addition, we investigate the use of a contrastive cost function for music-motion regulation. Experimental result demonstrate that the cost function improves the motion beat f-score.

The fast demographic growth, together with the concentration of the population in cities and the increasing amount of daily waste, are factors that push to the limit the ability of waste assimilation by Nature. Therefore, we need technological means to make an optimal management of the waste collection process, which represents 70% of the operational cost in waste treatment. In this article, we present a free intelligent software system, based on computational learning algorithms, which plans the best routes for waste collection supported by past (historical) and future (predictions) data. The objective of the system is the cost reduction of the waste collection service by means of the minimization in distance traveled by any truck to collect a container, hence the fuel consumption. At the same time the quality of service to the citizen is increased avoiding the annoying overflows of containers thanks to the accurate fill level predictions performed by BIN-CT. In this article we show the features of our software system, illustrating it operation with a real case study of a Spanish city. We conclude that the use of BIN-CT avoids unnecessary visits to containers, reduces the distance traveled to collect a container and therefore we obtain a reduction of total costs and harmful emissions thrown to the atmosphere.

In this paper, we analyze the Wisconsin Diagnostic Breast Cancer Data using Machine Learning classification techniques, such as the SVM, Bayesian Logistic Regression (Variational Approximation), and K-Nearest-Neighbors. We describe each model, and compare their performance through different measures. We conclude that SVM has the best performance among all other classifiers, while it competes closely with the Bayesian Logistic Regression that is ranked second best method for this dataset.

Forbes' November 2013 cover on how Michael Dell won the war to take his company private. "Dell Can't Lose," read the cover of Forbes Magazine on November 18, 2013 as we chronicled how personal computer billionaire Michael Dell relented against Carl Icahn to take his company private in what was dubbed "the nastiest tech buyout ever." If anything the cover was a tad understated. It's now clear Mr. Dell stands to make a fortune from Dell's privatization, turnaround, and inevitable return to public stock markets. So much so, here's an update on what it meant to be the victor: While Carl Icahn made a small profit challenging Dell for greenmail before ultimately ceding defeat, Michael Dell has accrued a paper fortune from the deal that is alone greater than the net worth of his onetime foe, Icahn.