Machine Learning
End-to-End Probabilistic Inference for Nonstationary Audio Analysis (1901.11436v3)
William J. Wilkinson, Michael Riis Andersen, Joshua D. Reiss, Dan Stowell, Arno Solin
2019-01-31
A typical audio signal processing pipeline includes multiple disjoint analysis stages, including calculation of a time-frequency representation followed by spectrogram-based feature analysis. We show how time-frequency analysis and nonnegative matrix factorisation can be jointly formulated as a spectral mixture Gaussian process model with nonstationary priors over the amplitude variance parameters. Further, we formulate this nonlinear model's state space representation, making it amenable to infinite-horizon Gaussian process regression with approximate inference via expectation propagation, which scales linearly in the number of time steps and quadratically in the state dimensionality. By doing so, we are able to process audio signals with hundreds of thousands of data points. We demonstrate, on various tasks with empirical data, how this inference scheme outperforms more standard techniques that rely on extended Kalman filtering.
Towards VQA Models that can Read (1904.08920v1)
Amanpreet Singh, Vivek Natarajan, Meet Shah, Yu Jiang, Xinlei Chen, Dhruv Batra, Devi Parikh, Marcus Rohrbach
2019-04-18
Studies have shown that a dominant class of questions asked by visually impaired users on images of their surroundings involves reading text in the image. But today's VQA models can not read! Our paper takes a first step towards addressing this problem. First, we introduce a new "TextVQA" dataset to facilitate progress on this important problem. Existing datasets either have a small proportion of questions about text (e.g., the VQA dataset) or are too small (e.g., the VizWiz dataset). TextVQA contains 45,336 questions on 28,408 images that require reasoning about text to answer. Second, we introduce a novel model architecture that reads text in the image, reasons about it in the context of the image and the question, and predicts an answer which might be a deduction based on the text and the image or composed of the strings found in the image. Consequently, we call our approach Look, Read, Reason & Answer (LoRRA). We show that LoRRA outperforms existing state-of-the-art VQA models on our TextVQA dataset. We find that the gap between human performance and machine performance is significantly larger on TextVQA than on VQA 2.0, suggesting that TextVQA is well-suited to benchmark progress along directions complementary to VQA 2.0.
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition (1904.08779v1)
Daniel S. Park, William Chan, Yu Zhang, Chung-Cheng Chiu, Barret Zoph, Ekin D. Cubuk, Quoc V. Le
2019-04-18
We present SpecAugment, a simple data augmentation method for speech recognition. SpecAugment is applied directly to the feature inputs of a neural network (i.e., filter bank coefficients). The augmentation policy consists of warping the features, masking blocks of frequency channels, and masking blocks of time steps. We apply SpecAugment on Listen, Attend and Spell networks for end-to-end speech recognition tasks. We achieve state-of-the-art performance on the LibriSpeech 960h and Swichboard 300h tasks, outperforming all prior work. On LibriSpeech, we achieve 6.8% WER on test-other without the use of a language model, and 5.8% WER with shallow fusion with a language model. This compares to the previous state-of-the-art hybrid system of 7.5% WER. For Switchboard, we achieve 7.2%/14.6% on the Switchboard/CallHome portion of the Hub5'00 test set without the use of a language model, and 6.8%/14.1% with shallow fusion, which compares to the previous state-of-the-art hybrid system at 8.3%/17.3% WER.
Decoding Molecular Graph Embeddings with Reinforcement Learning (1904.08915v1)
Steven Kearnes, Li Li, Patrick Riley
2019-04-18
We present RL-VAE, a graph-to-graph variational autoencoder that uses reinforcement learning to decode molecular graphs from latent embeddings. Methods have been described previously for graph-to-graph autoencoding, but these approaches require sophisticated decoders that increase the complexity of training and evaluation (such as requiring parallel encoders and decoders or non-trivial graph matching). Here, we repurpose a simple graph generator to enable efficient decoding and generation of molecular graphs.
MnasNet: Platform-Aware Neural Architecture Search for Mobile (1807.11626v2)
Mingxing Tan, Bo Chen, Ruoming Pang, Vijay Vasudevan, Mark Sandler, Andrew Howard, Quoc V. Le
2018-07-31
Designing convolutional neural networks (CNN) for mobile devices is challenging because mobile models need to be small and fast, yet still accurate. Although significant efforts have been dedicated to design and improve mobile CNNs on all dimensions, it is very difficult to manually balance these trade-offs when there are so many architectural possibilities to consider. In this paper, we propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency. Unlike previous work, where latency is considered via another, often inaccurate proxy (e.g., FLOPS), our approach directly measures real-world inference latency by executing the model on mobile phones. To further strike the right balance between flexibility and search space size, we propose a novel factorized hierarchical search space that encourages layer diversity throughout the network. Experimental results show that our approach consistently outperforms state-of-the-art mobile CNN models across multiple vision tasks. On the ImageNet classification task, our MnasNet achieves 75.2% top-1 accuracy with 78ms latency on a Pixel phone, which is 1.8x faster than MobileNetV2 [29] with 0.5% higher accuracy and 2.3x faster than NASNet [36] with 1.2% higher accuracy. Our MnasNet also achieves better mAP quality than MobileNets for COCO object detection. Code is at https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet
DScribe: Library of Descriptors for Machine Learning in Materials Science (1904.08875v1)
Lauri Himanen, Marc O. J. Jäger, Eiaki V. Morooka, Filippo Federici Canova, Yashasvi S. Ranawat, David Z. Gao, Patrick Rinke, Adam S. Foster
2019-04-18
DScribe is a software package for machine learning that provides popular feature transformations ("descriptors") for atomistic materials simulations. DScribe accelerates the application of machine learning for atomistic property prediction by providing user-friendly, off-the-shelf descriptor implementations. The package currently contains implementations for Coulomb matrix, Ewald sum matrix, sine matrix, Many-body Tensor Representation (MBTR), Atom-centered Symmetry Function (ACSF) and Smooth Overlap of Atomic Positions (SOAP). Usage of the package is illustrated for two different applications: formation energy prediction for solids and ionic charge prediction for atoms in organic molecules. The package is freely available under the open-source Apache License 2.0.
Hacking Google reCAPTCHA v3 using Reinforcement Learning (1903.01003v3)
Ismail Akrout, Amal Feriani, Mohamed Akrout
2019-03-03
We present a Reinforcement Learning (RL) methodology to bypass Google reCAPTCHA v3. We formulate the problem as a grid world where the agent learns how to move the mouse and click on the reCAPTCHA button to receive a high score. We study the performance of the agent when we vary the cell size of the grid world and show that the performance drops when the agent takes big steps toward the goal. Finally, we used a divide and conquer strategy to defeat the reCAPTCHA system for any grid resolution. Our proposed method achieves a success rate of 97.4% on a 100x100 grid and 96.7% on a 1000x1000 screen resolution.
Inspecting and Interacting with Meaningful Music Representations using VAE (1904.08842v1)
Ruihan Yang, Tianyao Chen, Yiyi Zhang, Gus Xia
2019-04-18
Variational Autoencoders(VAEs) have already achieved great results on image generation and recently made promising progress on music generation. However, the generation process is still quite difficult to control in the sense that the learned latent representations lack meaningful music semantics. It would be much more useful if people can modify certain music features, such as rhythm and pitch contour, via latent representations to test different composition ideas. In this paper, we propose a new method to inspect the pitch and rhythm interpretations of the latent representations and we name it disentanglement by augmentation. Based on the interpretable representations, an intuitive graphical user interface is designed for users to better direct the music creation process by manipulating the pitch contours and rhythmic complexity.
Neural-Attention-Based Deep Learning Architectures for Modeling Traffic Dynamics on Lane Graphs (1904.08831v1)
Matthew A. Wright, Simon F. G. Ehlers, Roberto Horowitz
2019-04-18
Deep neural networks can be powerful tools, but require careful application-specific design to ensure that the most informative relationships in the data are learnable. In this paper, we apply deep neural networks to the nonlinear spatiotemporal physics problem of vehicle traffic dynamics. We consider problems of estimating macroscopic quantities (e.g., the queue at an intersection) at a lane level. First-principles modeling at the lane scale has been a challenge due to complexities in modeling social behaviors like lane changes, and those behaviors' resultant macro-scale effects. Following domain knowledge that upstream/downstream lanes and neighboring lanes affect each others' traffic flows in distinct ways, we apply a form of neural attention that allows the neural network layers to aggregate information from different lanes in different manners. Using a microscopic traffic simulator as a testbed, we obtain results showing that an attentional neural network model can use information from nearby lanes to improve predictions, and, that explicitly encoding the lane-to-lane relationship types significantly improves performance. We also demonstrate the transfer of our learned neural network to a more complex road network, discuss how its performance degradation may be attributable to new traffic behaviors induced by increased topological complexity, and motivate learning dynamics models from many road network topologies.
Deep Residual Auto-Encoders for Expectation Maximization-based Dictionary Learning (1904.08827v1)
Bahareh Tolooshams, Sourav Dey, Demba Ba
2019-04-18
Convolutional dictionary learning (CDL) has become a popular method for learning sparse representations from data. State-of-the-art algorithms perform dictionary learning (DL) through an optimization-based alternating-minimization procedure that comprises a sparse coding and a dictionary update step respectively. Here, we draw connections between CDL and neural networks by proposing an architecture for CDL termed the constrained recurrent sparse auto-encoder (CRsAE). We leverage the interpretation of the alternating-minimization algorithm for DL as an Expectation-Maximization algorithm to develop auto-encoders (AEs) that, for the first time, enable the simultaneous training of the dictionary and regularization parameter. The forward pass of the encoder, which performs sparse coding, solves the E-step using an encoding matrix and a soft-thresholding non-linearity imposed by the FISTA algorithm. The encoder in this regard is a variant of residual and recurrent neural networks. The M-step is implemented via a two-stage back-propagation. In the first stage, we perform back-propagation through the AE formed by the encoder and a linear decoder whose parameters are tied to the encoder. This stage parallels the dictionary update step in DL. In the second stage, we update the regularization parameter by performing back-propagation through the encoder using a loss function that includes a prior on the parameter motivated by Bayesian statistics. We leverage GPUs to achieve significant computational gains relative to state-of-the-art optimization-based approaches to CDL. We apply CRsAE to spike sorting, the problem of identifying the time of occurrence of neural action potentials in recordings of electrical activity from the brain. We demonstrate on recordings lasting hours that CRsAE speeds up spike sorting by 900x compared to notoriously slow classical algorithms based on convex optimization.