Long Short-Term Memory (LSTM) is one of the most widely used recurrent structures in sequence modeling. It aims to use gates to control information flow (e.g., whether to skip some information or not) in the recurrent computations, although its practical implementation based on soft gates only partially achieves this goal. In this paper, we propose a new way for LSTM training, which pushes the output values of the gates towards 0 or 1. By doing so, we can better control the information flow: the gates are mostly open or closed, instead of in a middle state, which makes the results more interpretable. Empirical studies show that (1) Although it seems that we restrict the model capacity, there is no performance drop: we achieve better or comparable performances due to its better generalization ability; (2) The outputs of gates are not sensitive to their inputs: we can easily compress the LSTM unit in multiple ways, e.g., low-rank approximation and low-precision approximation. The compressed models are even better than the baseline models without compression.

Text classification has become indispensable due to the rapid increase of text in digital form. Over the past three decades, efforts have been made to approach this task using various learning algorithms and statistical models based on bag-of-words (BOW) features. Despite its simple implementation, BOW features lack semantic meaning representation. To solve this problem, neural networks started to be employed to learn word vectors, such as the word2vec. Word2vec embeds word semantic structure into vectors, where the angle between vectors indicates the meaningful similarity between words. To measure the similarity between texts, we propose the novel concept of word subspace, which can represent the intrinsic variability of features in a set of word vectors. Through this concept, it is possible to model text from word vectors while holding semantic information. To incorporate the word frequency directly in the subspace model, we further extend the word subspace to the term-frequency (TF) weighted word subspace. Based on these new concepts, text classification can be performed under the mutual subspace method (MSM) framework. The validity of our modeling is shown through experiments on the Reuters text database, comparing the results to various state-of-art algorithms.

Key to structured prediction is exploiting the problem structure to simplify the learning process. A major challenge arises when data exhibit a local structure (e.g., are made by "parts") that can be leveraged to better approximate the relation between (parts of) the input and (parts of) the output. Recent literature on signal processing, and in particular computer vision, has shown that capturing these aspects is indeed essential to achieve state-of-the-art performance. While such algorithms are typically derived on a case-by-case basis, in this work we propose the first theoretical framework to deal with part-based data from a general perspective. We derive a novel approach to deal with these problems and study its generalization properties within the setting of statistical learning theory. Our analysis is novel in that it explicitly quantifies the benefits of leveraging the part-based structure of the problem with respect to the learning rates of the proposed estimator.

The latest techniques from Neural Networks and Support Vector Machines (SVM) are used to investigate geometric properties of Complete Intersection Calabi-Yau (CICY) threefolds, a class of manifolds that facilitate string model building. An advanced neural network classifier and SVM are employed to (1) learn Hodge numbers and report a remarkable improvement over previous efforts, (2) query for favourability, and (3) predict discrete symmetries, a highly imbalanced problem to which the Synthetic Minority Oversampling Technique (SMOTE) is applied to boost performance. In each case study, we employ a genetic algorithm to optimise the hyperparameters of the neural network. We demonstrate that our approach provides quick diagnostic tools capable of shortlisting quasi-realistic string models based on compactification over smooth CICYs and further supports the paradigm that classes of problems in algebraic geometry can be machine learned.

The task of representing entire graphs has seen a surge of prominent results, mainly due to learning convolutional neural networks (CNNs) on graph-structured data. While CNNs demonstrate state-of-the-art performance in graph classification task, such methods are supervised and therefore steer away from the original problem of network representation in task-agnostic manner. Here, we coherently propose an approach for embedding entire graphs and show that our feature representations with SVM classifier increase classification accuracy of CNN algorithms and traditional graph kernels. For this we describe a recently discovered graph object, anonymous walk, on which we design task-independent algorithms for learning graph representations in explicit and distributed way. Overall, our work represents a new scalable unsupervised learning of state-of-the-art representations of entire graphs.

Analyzing large-scale, multi-experiment studies requires scientists to test each experimental outcome for statistical significance and then assess the results as a whole. We present Black Box FDR (BB-FDR), an empirical-Bayes method for analyzing multi-experiment studies when many covariates are gathered per experiment. BB-FDR learns a series of black box predictive models to boost power and control the false discovery rate (FDR) at two stages of study analysis. In Stage 1, it uses a deep neural network prior to report which experiments yielded significant outcomes. In Stage 2, a separate black box model of each covariate is used to select features that have significant predictive power across all experiments. In benchmarks, BB-FDR outperforms competing state-of-the-art methods in both stages of analysis. We apply BB-FDR to two real studies on cancer drug efficacy. For both studies, BB-FDR increases the proportion of significant outcomes discovered and selects variables that reveal key genomic drivers of drug sensitivity and resistance in cancer.

As Machine Learning (ML) gets applied to security-critical or sensitive domains, there is a growing need for integrity and privacy guarantees for ML computations running in untrusted environments. A pragmatic solution comes from Trusted Execution Environments, which use hardware and software protections to isolate sensitive computations from the untrusted software stack. However, these isolation guarantees come at a price in performance, compared to untrusted alternatives. This paper initiates the study of high performance execution of Deep Neural Networks (DNNs) in trusted environments by efficiently partitioning computations between trusted and untrusted devices. Building upon a simple secure outsourcing scheme for matrix multiplication, we propose Slalom, a framework that outsources execution of all linear layers in a DNN from any trusted environment (e.g., SGX, TrustZone or Sanctum) to a faster co-located device. We evaluate Slalom by executing DNNs in an Intel SGX enclave, which selectively outsources work to an untrusted GPU. For two canonical DNNs, VGG16 and MobileNet, we obtain 20x and 6x increases in throughput for verifiable inference, and 10x and 3.5x for verifiable and private inference.

We provide theoretical investigation of curriculum learning in the context of stochastic gradient descent when optimizing the convex linear regression loss. We prove that the rate of convergence of an ideal curriculum learning method is monotonically increasing with the difficulty of the examples. Moreover, among all equally difficult points, convergence is faster when using points which incur higher loss with respect to the current hypothesis. We then analyze curriculum learning in the context of training a CNN. We describe a method which infers the curriculum by way of transfer learning from another network, pre-trained on a different task. While this approach can only approximate the ideal curriculum, we observe empirically similar behavior to the one predicted by the theory, namely, a significant boost in convergence speed at the beginning of training. When the task is made more difficult, improvement in generalization performance is also observed. Finally, curriculum learning exhibits robustness against unfavorable conditions such as excessive regularization.

If the robotics world had a celebrity it would be Spot Mini of Boston Dynamics. Last month at the Robotics Summit in Boston the mechanical dog strutted onto the floor of the Westin Hotel trailed by hundreds of flickering iPhones. Marc Raibert first unveiled his metal menaagerie almost a decade ago with a video of Big Dog. Today, Mini is the fulfillment of his mission in a sleeker, smarter, and environmentally friendlier robo-canine package than its gas-burning ancestor. Since the early 1990s, machines have relied on rechargeable lithium ion batteries for power.

In a new 8,000-word set of ethicals principles and guidelines, Google outlined how it plans to manage--and in some cases limit--the application of artificial intelligence, a powerful and emerging set of technologies that Google views as key to its growth. Google, the primary business unit of Alphabet Inc., GOOGL -1.09% has recently come under criticism from its own employees for supplying image-recognition technology to the U.S. Department of Defense, in a partnership called Project Maven. Google told employees earlier this month it wouldn't seek to renew its contract for Project Maven, a person familiar with the matter said at the time, and that decision in turn was blasted by some who said the company shouldn't be conflicted about supporting national security. Google's artificial intelligence also recently generated public alarm after the company demonstrated a robotic voice that can trick humans into thinking it is real. Google is having to expand its definition of ethics as its technology seeps more and more into the institutions of public life, from scientific research to military intelligence.