# Trending arXiv

Note: this version is tailored to @Smerity - though you can run your own! Trending arXiv may eventually be extended to multiple users ...

### Papers

1 2 3 4 5 6 7 8 9 30 31

#### Peephole: Predicting Network Performance Before Training

Boyang Deng, Junjie Yan, Dahua Lin

The quest for performant networks has been a significant force that drives the advancements of deep learning in recent years. While rewarding, improving network design has never been an easy journey. The large design space combined with the tremendous cost required for network training poses a major obstacle to this endeavor. In this work, we propose a new approach to this problem, namely, predicting the performance of a network before training, based on its architecture. Specifically, we develop a unified way to encode individual layers into vectors and bring them together to form an integrated description via LSTM. Taking advantage of the recurrent network's strong expressive power, this method can reliably predict the performances of various network architectures. Our empirical studies showed that it not only achieved accurate predictions but also produced consistent rankings across datasets -- a key desideratum in performance prediction.

Captured tweets and retweets: 24

#### Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, Timothy Lillicrap, Karen Simonyan, Demis Hassabis

The game of chess is the most widely-studied domain in the history of artificial intelligence. The strongest programs are based on a combination of sophisticated search techniques, domain-specific adaptations, and handcrafted evaluation functions that have been refined by human experts over several decades. In contrast, the AlphaGo Zero program recently achieved superhuman performance in the game of Go, by tabula rasa reinforcement learning from games of self-play. In this paper, we generalise this approach into a single AlphaZero algorithm that can achieve, tabula rasa, superhuman performance in many challenging domains. Starting from random play, and given no domain knowledge except the game rules, AlphaZero achieved within 24 hours a superhuman level of play in the games of chess and shogi (Japanese chess) as well as Go, and convincingly defeated a world-champion program in each case.

Captured tweets and retweets: 1

#### Progressive Neural Architecture Search

Chenxi Liu, Barret Zoph, Jonathon Shlens, Wei Hua, Li-Jia Li, Li Fei-Fei, Alan Yuille, Jonathan Huang, Kevin Murphy

We propose a method for learning CNN structures that is more efficient than previous approaches: instead of using reinforcement learning (RL) or genetic algorithms (GA), we use a sequential model-based optimization (SMBO) strategy, in which we search for architectures in order of increasing complexity, while simultaneously learning a surrogate function to guide the search, similar to A* search. On the CIFAR-10 dataset, our method finds a CNN structure with the same classification accuracy (3.41% error rate) as the RL method of Zoph et al. (2017), but 2 times faster (in terms of number of models evaluated). It also outperforms the GA method of Liu et al. (2017), which finds a model with worse performance (3.63% error rate), and takes 5 times longer. Finally we show that the model we learned on CIFAR also works well at the task of ImageNet classification. In particular, we match the state-of-the-art performance of 82.9% top-1 and 96.1% top-5 accuracy.

Captured tweets and retweets: 2

#### Deep Learning Scaling is Predictable, Empirically

Joel Hestness, Sharan Narang, Newsha Ardalani, Gregory Diamos, Heewoo Jun, Hassan Kianinejad, Md. Mostofa Ali Patwary, Yang Yang, Yanqi Zhou

Deep learning (DL) creates impactful advances following a virtuous recipe: model architecture search, creating large training data sets, and scaling computation. It is widely believed that growing training sets and models should improve accuracy and result in better products. As DL application domains grow, we would like a deeper understanding of the relationships between training set size, computational scale, and model accuracy improvements to advance the state-of-the-art. This paper presents a large scale empirical characterization of generalization error and model size growth as training sets grow. We introduce a methodology for this measurement and test four machine learning domains: machine translation, language modeling, image processing, and speech recognition. Our empirical results show power-law generalization error scaling across a breadth of factors, resulting in power-law exponents---the "steepness" of the learning curve---yet to be explained by theoretical work. Further, model improvements only shift the error but do not appear to affect the power-law exponent. We also show that model size scales sublinearly with data size. These scaling relationships have significant implications on deep learning research, practice, and systems. They can assist model debugging, setting accuracy targets, and decisions about data set growth. They can also guide computing system design and underscore the importance of continued computational scaling.

Captured tweets and retweets: 8

#### Wavenet based low rate speech coding

W. Bastiaan Kleijn, Felicia S. C. Lim, Alejandro Luebs, Jan Skoglund, Florian Stimberg, Quan Wang, Thomas C. Walters

Traditional parametric coding of speech facilitates low rate but provides poor reconstruction quality because of the inadequacy of the model used. We describe how a WaveNet generative speech model can be used to generate high quality speech from the bit stream of a standard parametric coder operating at 2.4 kb/s. We compare this parametric coder with a waveform coder based on the same generative model and show that approximating the signal waveform incurs a large rate penalty. Our experiments confirm the high performance of the WaveNet based coder and show that the speech produced by the system is able to additionally perform implicit bandwidth extension and does not significantly impair recognition of the original speaker for the human listener, even when that speaker has not been used during the training of the generative model.

Captured tweets and retweets: 2

#### Parallel WaveNet: Fast High-Fidelity Speech Synthesis

Aaron van den Oord, Yazhe Li, Igor Babuschkin, Karen Simonyan, Oriol Vinyals, Koray Kavukcuoglu, George van den Driessche, Edward Lockhart, Luis C. Cobo, Florian Stimberg, Norman Casagrande, Dominik Grewe, Seb Noury, Sander Dieleman, Erich Elsen, Nal Kalchbrenner, Heiga Zen, Alex Graves, Helen King, Tom Walters, Dan Belov, Demis Hassabis

The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous system. However, because WaveNet relies on sequential generation of one audio sample at a time, it is poorly suited to today's massively parallel computers, and therefore hard to deploy in a real-time production setting. This paper introduces Probability Density Distillation, a new method for training a parallel feed-forward network from a trained WaveNet with no significant difference in quality. The resulting system is capable of generating high-fidelity speech samples at more than 20 times faster than real-time, and is deployed online by Google Assistant, including serving multiple English and Japanese voices.

Captured tweets and retweets: 1

#### Neural Text Generation: A Practical Guide

Ziang Xie

Deep learning methods have recently achieved great empirical success on machine translation, dialogue response generation, summarization, and other text generation tasks. At a high level, the technique has been to train end-to-end neural network models consisting of an encoder model to produce a hidden representation of the source text, followed by a decoder model to generate the target. While such models have significantly fewer pieces than earlier systems, significant tuning is still required to achieve good performance. For text generation models in particular, the decoder can behave in undesired ways, such as by generating truncated or repetitive outputs, outputting bland and generic responses, or in some cases producing ungrammatical gibberish. This paper is intended as a practical guide for resolving such undesired behavior in text generation models, with the aim of helping enable real-world applications.

Captured tweets and retweets: 3

#### The Doctor Just Won't Accept That!

Zachary C. Lipton

Calls to arms to build interpretable models express a well-founded discomfort with machine learning. Should a software agent that does not even know what a loan is decide who qualifies for one? Indeed, we ought to be cautious about injecting machine learning (or anything else, for that matter) into applications where there may be a significant risk of causing social harm. However, claims that stakeholders "just won't accept that!" do not provide a sufficient foundation for a proposed field of study. For the field of interpretable machine learning to advance, we must ask the following questions: What precisely won't various stakeholders accept? What do they want? Are these desiderata reasonable? Are they feasible? In order to answer these questions, we'll have to give real-world problems and their respective stakeholders greater consideration.

Captured tweets and retweets: 14

#### Hello Edge: Keyword Spotting on Microcontrollers

Yundong Zhang, Naveen Suda, Liangzhen Lai, Vikas Chandra

Keyword spotting (KWS) is a critical component for enabling speech based user interactions on smart devices. It requires real-time response and high accuracy for good user experience. Recently, neural networks have become an attractive choice for KWS architecture because of their superior accuracy compared to traditional speech processing algorithms. Due to its always-on nature, KWS application has highly constrained power budget and typically runs on tiny microcontrollers with limited memory and compute capability. The design of neural network architecture for KWS must consider these constraints. In this work, we perform neural network architecture evaluation and exploration for running KWS on resource-constrained microcontrollers. We train various neural network architectures for keyword spotting published in literature to compare their accuracy and memory/compute requirements. We show that it is possible to optimize these neural network architectures to fit within the memory and compute constraints of microcontrollers without sacrificing accuracy. We further explore the depthwise separable convolutional neural network (DS-CNN) and compare it against other neural network architectures. DS-CNN achieves an accuracy of 95.4%, which is ~10% higher than the DNN model with similar number of parameters.

Captured tweets and retweets: 1

#### Recurrent Neural Networks as Weighted Language Recognizers

Yining Chen, Sorcha Gilroy, Kevin Knight, Jonathan May

We investigate computational complexity of questions of various problems for simple recurrent neural networks (RNNs) as formal models for recognizing weighted languages. We focus on the single-layer, ReLU-activation, rational-weight RNNs with softmax, which are commonly used in natural language processing applications. We show that most problems for such RNNs are undecidable, including consistency, equivalence, minimization, and finding the highest-weighted string. However, for consistent RNNs the last problem becomes decidable, although the solution can be exponentially long. If additionally the string is limited to polynomial length, the problem becomes NP-complete and APX-hard. In summary, this shows that approximations and heuristic algorithms are necessary in practical applications of those RNNs. We also consider RNNs as unweighted language recognizers and situate RNNs between Turing Machines and Random-Access Machines regarding their real-time recognition powers.

Captured tweets and retweets: 2

#### Improving Factor-Based Quantitative Investing by Forecasting Company Fundamentals

John Alberg, Zachary C. Lipton

On a periodic basis, publicly traded companies are required to report fundamentals: financial data such as revenue, operating income, debt, among others. These data points provide some insight into the financial health of a company. Academic research has identified some factors, i.e. computed features of the reported data, that are known through retrospective analysis to outperform the market average. Two popular factors are the book value normalized by market capitalization (book-to-market) and the operating income normalized by the enterprise value (EBIT/EV). In this paper: we first show through simulation that if we could (clairvoyantly) select stocks using factors calculated on future fundamentals (via oracle), then our portfolios would far outperform a standard factor approach. Motivated by this analysis, we train deep neural networks to forecast future fundamentals based on a trailing 5-years window. Quantitative analysis demonstrates a significant improvement in MSE over a naive strategy. Moreover, in retrospective analysis using an industry-grade stock portfolio simulator (backtester), we show an improvement in compounded annual return to 17.1% (MLP) vs 14.4% for a standard factor model.

Captured tweets and retweets: 3

#### Learning Explanatory Rules from Noisy Data

Richard Evans, Edward Grefenstette

Artificial Neural Networks are powerful function approximators capable of modelling solutions to a wide variety of problems, both supervised and unsupervised. As their size and expressivity increases, so too does the variance of the model, yielding a nearly ubiquitous overfitting problem. Although mitigated by a variety of model regularisation methods, the common cure is to seek large amounts of training data---which is not necessarily easily obtained---that sufficiently approximates the data distribution of the domain we wish to test on. In contrast, logic programming methods such as Inductive Logic Programming offer an extremely data-efficient process by which models can be trained to reason on symbolic domains. However, these methods are unable to deal with the variety of domains neural networks can be applied to: they are not robust to noise in or mislabelling of inputs, and perhaps more importantly, cannot be applied to non-symbolic domains where the data is ambiguous, such as operating on raw pixels. In this paper, we propose a Differentiable Inductive Logic framework ($\partial$ILP), which can not only solve tasks which traditional ILP systems are suited for, but shows a robustness to noise and error in the training data which ILP cannot cope with. Furthermore, as it is trained by backpropagation against a likelihood objective, it can be hybridised by connecting it with neural networks over ambiguous data in order to be applied to domains which ILP cannot address, while providing data efficiency and generalisation beyond what neural networks on their own can achieve.

Captured tweets and retweets: 1

#### Unbounded cache model for online language modeling with open vocabulary

Edouard Grave, Moustapha Cisse, Armand Joulin

Recently, continuous cache models were proposed as extensions to recurrent neural network language models, to adapt their predictions to local changes in the data distribution. These models only capture the local context, of up to a few thousands tokens. In this paper, we propose an extension of continuous cache models, which can scale to larger contexts. In particular, we use a large scale non-parametric memory component that stores all the hidden activations seen in the past. We leverage recent advances in approximate nearest neighbor search and quantization algorithms to store millions of representations while searching them efficiently. We conduct extensive experiments showing that our approach significantly improves the perplexity of pre-trained language models on new distributions, and can scale efficiently to much larger contexts than previously proposed local cache models.

Captured tweets and retweets: 2

#### End-to-end learning for music audio tagging at scale

Jordi Pons, Oriol Nieto, Matthew Prockup, Erik Schmidt, Andreas Ehmann, Xavier Serra

The lack of data tends to limit the outcomes of deep learning research, particularly when dealing with end-to-end learning stacks processing raw data such as waveforms. In this study, 1.2M tracks annotated with musical labels are available to train our end-to-end models. This large amount of data allows us to unrestrictedly explore two different design paradigms for music auto-tagging: assumption-free models - using waveforms as input with very small convolutional filters; and models that rely on domain knowledge - log-mel spectrograms with a convolutional neural network designed to learn timbral and temporal features. Our work focuses on studying how these two types of deep architectures perform when datasets of variable size are available for training: the MagnaTagATune (25k songs), the Million Song Dataset (240k songs), and a private dataset of 1.2M songs. Our experiments suggest that music domain assumptions are relevant when not enough training data are available, thus showing how waveform-based models outperform spectrogram-based ones in large-scale data scenarios.

Captured tweets and retweets: 2

#### Large-Scale Optimal Transport and Mapping Estimation

Vivien Seguy, Bharath Bhushan Damodaran, Rémi Flamary, Nicolas Courty, Antoine Rolet, Mathieu Blondel

This paper presents a novel two-step approach for the fundamental problem of learning an optimal map from one distribution to another. First, we learn an optimal transport (OT) plan, which can be thought as a one-to-many map between the two distributions. To that end, we propose a stochastic dual approach of regularized OT, and show empirically that it scales better than a recent related approach when the amount of samples is very large. Second, we estimate a \textit{Monge map} as a deep neural network learned by approximating the barycentric projection of the previously-obtained OT plan. This parameterization allows generalization of the mapping outside the support of the input measure. We prove two theoretical stability results of regularized OT which show that our estimations converge to the OT plan and Monge map between the underlying continuous measures. We showcase our proposed approach on two applications: domain adaptation and generative modeling.

Captured tweets and retweets: 2

#### Neural Discrete Representation Learning

Aaron van den Oord, Oriol Vinyals, Koray Kavukcuoglu

Learning useful representations without supervision remains a key challenge in machine learning. In this paper, we propose a simple yet powerful generative model that learns such discrete representations. Our model, the Vector Quantised-Variational AutoEncoder (VQ-VAE), differs from VAEs in two key ways: the encoder network outputs discrete, rather than continuous, codes; and the prior is learnt rather than static. In order to learn a discrete latent representation, we incorporate ideas from vector quantisation (VQ). Using the VQ method allows the model to circumvent issues of "posterior collapse" -- where the latents are ignored when they are paired with a powerful autoregressive decoder -- typically observed in the VAE framework. Pairing these representations with an autoregressive prior, the model can generate high quality images, videos, and speech as well as doing high quality speaker conversion and unsupervised learning of phonemes, providing further evidence of the utility of the learnt representations.

Captured tweets and retweets: 116

#### An Information-Theoretic Analysis of Deep Latent-Variable Models

Alexander A. Alemi, Ben Poole, Ian Fischer, Joshua V. Dillon, Rif A. Saurous, Kevin Murphy

We present an information-theoretic framework for understanding trade-offs in unsupervised learning of deep latent-variables models using variational inference. This framework emphasizes the need to consider latent-variable models along two dimensions: the ability to reconstruct inputs (distortion) and the communication cost (rate). We derive the optimal frontier of generative models in the two-dimensional rate-distortion plane, and show how the standard evidence lower bound objective is insufficient to select between points along this frontier. However, by performing targeted optimization to learn generative models with different rates, we are able to learn many models that can achieve similar generative performance but make vastly different trade-offs in terms of the usage of the latent variable. Through experiments on MNIST and Omniglot with a variety of architectures, we show how our framework sheds light on many recent proposed extensions to the variational autoencoder family.

Captured tweets and retweets: 1

#### Still not systematic after all these years: On the compositional skills of sequence-to-sequence recurrent networks

Brenden M. Lake, Marco Baroni

Humans can understand and produce new utterances effortlessly, thanks to their systematic compositional skills. Once a person learns the meaning of a new verb "dax," he or she can immediately understand the meaning of "dax twice" or "sing and dax." In this paper, we introduce the SCAN domain, consisting of a set of simple compositional navigation commands paired with the corresponding action sequences. We then test the zero-shot generalization capabilities of a variety of recurrent neural networks (RNNs) trained on SCAN with sequence-to-sequence methods. We find that RNNs can generalize well when the differences between training and test commands are small, so that they can apply "mix-and-match" strategies to solve the task. However, when generalization requires systematic compositional skills (as in the "dax" example above), RNNs fail spectacularly. We conclude with a proof-of-concept experiment in neural machine translation, supporting the conjecture that lack of systematicity is an important factor explaining why neural networks need very large training sets.

Captured tweets and retweets: 2

#### JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis

Ryosuke Sonobe, Shinnosuke Takamichi, Hiroshi Saruwatari

Thanks to improvements in machine learning techniques including deep learning, a free large-scale speech corpus that can be shared between academic institutions and commercial companies has an important role. However, such a corpus for Japanese speech synthesis does not exist. In this paper, we designed a novel Japanese speech corpus, named the "JSUT corpus," that is aimed at achieving end-to-end speech synthesis. The corpus consists of 10 hours of reading-style speech data and its transcription and covers all of the main pronunciations of daily-use Japanese characters. In this paper, we describe how we designed and analyzed the corpus. The corpus is freely available online.

Captured tweets and retweets: 2

#### Deep Residual Learning for Small-Footprint Keyword Spotting

Raphael Tang, Jimmy Lin

We explore the application of deep residual learning and dilated convolutions to the keyword spotting task, using the recently-released Google Speech Commands Dataset as our benchmark. Our best residual network (ResNet) implementation significantly outperforms Google's previous convolutional neural networks in terms of accuracy. By varying model depth and width, we can achieve compact models that also outperform previous small-footprint variants. To our knowledge, we are the first to examine these approaches for keyword spotting, and our results establish an open-source state-of-the-art reference to support the development of future speech-based interfaces.

Captured tweets and retweets: 1

1 2 3 4 5 6 7 8 9 30 31