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 25 26

A Brief Survey of Deep Reinforcement Learning

Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage, Anil Anthony Bharath

Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement learning to scale to problems that were previously intractable, such as learning to play video games directly from pixels. Deep reinforcement learning algorithms are also applied to robotics, allowing control policies for robots to be learned directly from camera inputs in the real world. In this survey, we begin with an introduction to the general field of reinforcement learning, then progress to the main streams of value-based and policy-based methods. Our survey will cover central algorithms in deep reinforcement learning, including the deep $Q$-network, trust region policy optimisation, and asynchronous advantage actor-critic. In parallel, we highlight the unique advantages of deep neural networks, focusing on visual understanding via reinforcement learning. To conclude, we describe several current areas of research within the field.

Captured tweets and retweets: 1

Toward Geometric Deep SLAM

Daniel DeTone, Tomasz Malisiewicz, Andrew Rabinovich

We present a point tracking system powered by two deep convolutional neural networks. The first network, MagicPoint, operates on single images and extracts salient 2D points. The extracted points are "SLAM-ready" because they are by design isolated and well-distributed throughout the image. We compare this network against classical point detectors and discover a significant performance gap in the presence of image noise. As transformation estimation is more simple when the detected points are geometrically stable, we designed a second network, MagicWarp, which operates on pairs of point images (outputs of MagicPoint), and estimates the homography that relates the inputs. This transformation engine differs from traditional approaches because it does not use local point descriptors, only point locations. Both networks are trained with simple synthetic data, alleviating the requirement of expensive external camera ground truthing and advanced graphics rendering pipelines. The system is fast and lean, easily running 30+ FPS on a single CPU.

Captured tweets and retweets: 2

Voice Synthesis for in-the-Wild Speakers via a Phonological Loop

Yaniv Taigman, Lior Wolf, Adam Polyak, Eliya Nachmani

We present a new neural text to speech method that is able to transform text to speech in voices that are sampled in the wild. Unlike other text to speech systems, our solution is able to deal with unconstrained samples obtained from public speeches. The network architecture is simpler than those in the existing literature and is based on a novel shifting buffer working memory. The same buffer is used for estimating the attention, computing the output audio, and for updating the buffer itself. The input sentence is encoded using a context-free lookup table that contains one entry per character or phoneme. Lastly, the speakers are similarly represented by a short vector that can also be fitted to new speakers and variability in the generated speech is achieved by priming the buffer prior to generating the audio. Experimental results on two datasets demonstrate convincing multi-speaker and in-the-wild capabilities. In order to promote reproducibility, we release our source code and models: PyTorch code and sample audio files are available at ytaigman.github.io/loop.

Captured tweets and retweets: 2

On the State of the Art of Evaluation in Neural Language Models

Gábor Melis, Chris Dyer, Phil Blunsom

Ongoing innovations in recurrent neural network architectures have provided a steady influx of apparently state-of-the-art results on language modelling benchmarks. However, these have been evaluated using differing code bases and limited computational resources, which represent uncontrolled sources of experimental variation. We reevaluate several popular architectures and regularisation methods with large-scale automatic black-box hyperparameter tuning and arrive at the somewhat surprising conclusion that standard LSTM architectures, when properly regularised, outperform more recent models. We establish a new state of the art on the Penn Treebank and Wikitext-2 corpora, as well as strong baselines on the Hutter Prize dataset.

Captured tweets and retweets: 2

Learning like humans with Deep Symbolic Networks

Qunzhi Zhang, Didier Sornette

We introduce the Deep Symbolic Network (DSN) model, which aims at becoming the white-box version of Deep Neural Networks (DNN). The DSN model provides a simple, universal yet powerful structure, similar to DNN, to represent any knowledge of the world, which is transparent to humans. The conjecture behind the DSN model is that any type of real world objects sharing enough common features are mapped into human brains as a symbol. Those symbols are connected by links, representing the composition, correlation, causality, or other relationships between them, forming a deep, hierarchical symbolic network structure. Powered by such a structure, the DSN model is expected to learn like humans, because of its unique characteristics. First, it is universal, using the same structure to store any knowledge. Second, it can learn symbols from the world and construct the deep symbolic networks automatically, by utilizing the fact that real world objects have been naturally separated by singularities. Third, it is symbolic, with the capacity of performing causal deduction and generalization. Fourth, the symbols and the links between them are transparent to us, and thus we will know what it has learned or not - which is the key for the security of an AI system. Fifth, its transparency enables it to learn with relatively small data. Sixth, its knowledge can be accumulated. Last but not least, it is more friendly to unsupervised learning than DNN. We present the details of the model, the algorithm powering its automatic learning ability, and describe its usefulness in different use cases. The purpose of this paper is to generate broad interest to develop it within an open source project centered on the Deep Symbolic Network (DSN) model towards the development of general AI.

Captured tweets and retweets: 1

Controlling Linguistic Style Aspects in Neural Language Generation

Jessica Ficler, Yoav Goldberg

Most work on neural natural language generation (NNLG) focus on controlling the content of the generated text. We experiment with controlling several stylistic aspects of the generated text, in addition to its content. The method is based on conditioned RNN language model, where the desired content as well as the stylistic parameters serve as conditioning contexts. We demonstrate the approach on the movie reviews domain and show that it is successful in generating coherent sentences corresponding to the required linguistic style and content.

Captured tweets and retweets: 2

Emergence of Locomotion Behaviours in Rich Environments

Nicolas Heess, Dhruva TB, Srinivasan Sriram, Jay Lemmon, Josh Merel, Greg Wayne, Yuval Tassa, Tom Erez, Ziyu Wang, Ali Eslami, Martin Riedmiller, David Silver

The reinforcement learning paradigm allows, in principle, for complex behaviours to be learned directly from simple reward signals. In practice, however, it is common to carefully hand-design the reward function to encourage a particular solution, or to derive it from demonstration data. In this paper explore how a rich environment can help to promote the learning of complex behavior. Specifically, we train agents in diverse environmental contexts, and find that this encourages the emergence of robust behaviours that perform well across a suite of tasks. We demonstrate this principle for locomotion -- behaviours that are known for their sensitivity to the choice of reward. We train several simulated bodies on a diverse set of challenging terrains and obstacles, using a simple reward function based on forward progress. Using a novel scalable variant of policy gradient reinforcement learning, our agents learn to run, jump, crouch and turn as required by the environment without explicit reward-based guidance. A visual depiction of highlights of the learned behavior can be viewed in this $\href{https://goo.gl/8rTx2F}{video}$ .

Captured tweets and retweets: 2

Teacher-Student Curriculum Learning

Tambet Matiisen, Avital Oliver, Taco Cohen, John Schulman

We propose Teacher-Student Curriculum Learning (TSCL), a framework for automatic curriculum learning, where the Student tries to learn a complex task and the Teacher automatically chooses subtasks from a given set for the Student to train on. We describe a family of Teacher algorithms that rely on the intuition that the Student should practice more those tasks on which it makes the fastest progress, i.e. where the slope of the learning curve is highest. In addition, the Teacher algorithms address the problem of forgetting by also choosing tasks where the Student's performance is getting worse. We demonstrate that TSCL matches or surpasses the results of carefully hand-crafted curricula in two tasks: addition of decimal numbers with LSTM and navigation in Minecraft. Using our automatically generated curriculum enabled to solve a Minecraft maze that could not be solved at all when training directly on solving the maze, and the learning was an order of magnitude faster than uniform sampling of subtasks.

Captured tweets and retweets: 2

You Are How You Walk: Uncooperative MoCap Gait Identification for Video Surveillance with Incomplete and Noisy Data

Michal Balazia, Petr Sojka

This work offers a design of a video surveillance system based on a soft biometric -- gait identification from MoCap data. The main focus is on two substantial issues of the video surveillance scenario: (1) the walkers do not cooperate in providing learning data to establish their identities and (2) the data are often noisy or incomplete. We show that only a few examples of human gait cycles are required to learn a projection of raw MoCap data onto a low-dimensional sub-space where the identities are well separable. Latent features learned by Maximum Margin Criterion (MMC) method discriminate better than any collection of geometric features. The MMC method is also highly robust to noisy data and works properly even with only a fraction of joints tracked. The overall workflow of the design is directly applicable for a day-to-day operation based on the available MoCap technology and algorithms for gait analysis. In the concept we introduce, a walker's identity is represented by a cluster of gait data collected at their incidents within the surveillance system: They are how they walk.

Captured tweets and retweets: 1

Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study

Samuel Ritter, David G. T. Barrett, Adam Santoro, Matt M. Botvinick

Deep neural networks (DNNs) have achieved unprecedented performance on a wide range of complex tasks, rapidly outpacing our understanding of the nature of their solutions. This has caused a recent surge of interest in methods for rendering modern neural systems more interpretable. In this work, we propose to address the interpretability problem in modern DNNs using the rich history of problem descriptions, theories and experimental methods developed by cognitive psychologists to study the human mind. To explore the potential value of these tools, we chose a well-established analysis from developmental psychology that explains how children learn word labels for objects, and applied that analysis to DNNs. Using datasets of stimuli inspired by the original cognitive psychology experiments, we find that state-of-the-art one shot learning models trained on ImageNet exhibit a similar bias to that observed in humans: they prefer to categorize objects according to shape rather than color. The magnitude of this shape bias varies greatly among architecturally identical, but differently seeded models, and even fluctuates within seeds throughout training, despite nearly equivalent classification performance. These results demonstrate the capability of tools from cognitive psychology for exposing hidden computational properties of DNNs, while concurrently providing us with a computational model for human word learning.

Captured tweets and retweets: 1

Gated-Attention Architectures for Task-Oriented Language Grounding

Devendra Singh Chaplot, Kanthashree Mysore Sathyendra, Rama Kumar Pasumarthi, Dheeraj Rajagopal, Ruslan Salakhutdinov

To perform tasks specified by natural language instructions, autonomous agents need to extract semantically meaningful representations of language and map it to visual elements and actions in the environment. This problem is called task-oriented language grounding. We propose an end-to-end trainable neural architecture for task-oriented language grounding in 3D environments which assumes no prior linguistic or perceptual knowledge and requires only raw pixels from the environment and the natural language instruction as input. The proposed model combines the image and text representations using a Gated-Attention mechanism and learns a policy to execute the natural language instruction using standard reinforcement and imitation learning methods. We show the effectiveness of the proposed model on unseen instructions as well as unseen maps, both quantitatively and qualitatively. We also introduce a novel environment based on a 3D game engine to simulate the challenges of task-oriented language grounding over a rich set of instructions and environment states.

Captured tweets and retweets: 1

Constrained Bayesian Optimization with Noisy Experiments

Benjamin Letham, Brian Karrer, Guilherme Ottoni, Eytan Bakshy

Randomized experiments are the gold standard for evaluating the effects of changes to real-world systems, including Internet services. Data in these tests may be difficult to collect and outcomes may have high variance, resulting in potentially large measurement error. Bayesian optimization is a promising technique for optimizing multiple continuous parameters for field experiments, but existing approaches degrade in performance when the noise level is high. We derive an exact expression for expected improvement under greedy batch optimization with noisy observations and noisy constraints, and develop a quasi-Monte Carlo approximation that allows it to be efficiently optimized. Experiments with synthetic functions show that optimization performance on noisy, constrained problems outperforms existing methods. We further demonstrate the effectiveness of the method with two real experiments conducted at Facebook: optimizing a production ranking system, and optimizing web server compiler flags.

Captured tweets and retweets: 2

SEP-Nets: Small and Effective Pattern Networks

Zhe Li, Xiaoyu Wang, Xutao Lv, Tianbao Yang

While going deeper has been witnessed to improve the performance of convolutional neural networks (CNN), going smaller for CNN has received increasing attention recently due to its attractiveness for mobile/embedded applications. It remains an active and important topic how to design a small network while retaining the performance of large and deep CNNs (e.g., Inception Nets, ResNets). Albeit there are already intensive studies on compressing the size of CNNs, the considerable drop of performance is still a key concern in many designs. This paper addresses this concern with several new contributions. First, we propose a simple yet powerful method for compressing the size of deep CNNs based on parameter binarization. The striking difference from most previous work on parameter binarization/quantization lies at different treatments of $1\times 1$ convolutions and $k\times k$ convolutions ($k>1$), where we only binarize $k\times k$ convolutions into binary patterns. The resulting networks are referred to as pattern networks. By doing this, we show that previous deep CNNs such as GoogLeNet and Inception-type Nets can be compressed dramatically with marginal drop in performance. Second, in light of the different functionalities of $1\times 1$ (data projection/transformation) and $k\times k$ convolutions (pattern extraction), we propose a new block structure codenamed the pattern residual block that adds transformed feature maps generated by $1\times 1$ convolutions to the pattern feature maps generated by $k\times k$ convolutions, based on which we design a small network with $\sim 1$ million parameters. Combining with our parameter binarization, we achieve better performance on ImageNet than using similar sized networks including recently released Google MobileNets.

Captured tweets and retweets: 7

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.0 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

Captured tweets and retweets: 4

Deep reinforcement learning from human preferences

Paul Christiano, Jan Leike, Tom B. Brown, Miljan Martic, Shane Legg, Dario Amodei

For sophisticated reinforcement learning (RL) systems to interact usefully with real-world environments, we need to communicate complex goals to these systems. In this work, we explore goals defined in terms of (non-expert) human preferences between pairs of trajectory segments. We show that this approach can effectively solve complex RL tasks without access to the reward function, including Atari games and simulated robot locomotion, while providing feedback on less than one percent of our agent's interactions with the environment. This reduces the cost of human oversight far enough that it can be practically applied to state-of-the-art RL systems. To demonstrate the flexibility of our approach, we show that we can successfully train complex novel behaviors with about an hour of human time. These behaviors and environments are considerably more complex than any that have been previously learned from human feedback.

Captured tweets and retweets: 2

Self-Normalizing Neural Networks

Günter Klambauer, Thomas Unterthiner, Andreas Mayr, Sepp Hochreiter

Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural networks (RNNs). However, success stories of Deep Learning with standard feed-forward neural networks (FNNs) are rare. FNNs that perform well are typically shallow and, therefore cannot exploit many levels of abstract representations. We introduce self-normalizing neural networks (SNNs) to enable high-level abstract representations. While batch normalization requires explicit normalization, neuron activations of SNNs automatically converge towards zero mean and unit variance. The activation function of SNNs are "scaled exponential linear units" (SELUs), which induce self-normalizing properties. Using the Banach fixed-point theorem, we prove that activations close to zero mean and unit variance that are propagated through many network layers will converge towards zero mean and unit variance -- even under the presence of noise and perturbations. This convergence property of SNNs allows to (1) train deep networks with many layers, (2) employ strong regularization, and (3) to make learning highly robust. Furthermore, for activations not close to unit variance, we prove an upper and lower bound on the variance, thus, vanishing and exploding gradients are impossible. We compared SNNs on (a) 121 tasks from the UCI machine learning repository, on (b) drug discovery benchmarks, and on (c) astronomy tasks with standard FNNs and other machine learning methods such as random forests and support vector machines. SNNs significantly outperformed all competing FNN methods at 121 UCI tasks, outperformed all competing methods at the Tox21 dataset, and set a new record at an astronomy data set. The winning SNN architectures are often very deep. Implementations are available at: github.com/bioinf-jku/SNNs.

Captured tweets and retweets: 2

Parameter Space Noise for Exploration

Matthias Plappert, Rein Houthooft, Prafulla Dhariwal, Szymon Sidor, Richard Y. Chen, Xi Chen, Tamim Asfour, Pieter Abbeel, Marcin Andrychowicz

Deep reinforcement learning (RL) methods generally engage in exploratory behavior through noise injection in the action space. An alternative is to add noise directly to the agent's parameters, which can lead to more consistent exploration and a richer set of behaviors. Methods such as evolutionary strategies use parameter perturbations, but discard all temporal structure in the process and require significantly more samples. Combining parameter noise with traditional RL methods allows to combine the best of both worlds. We demonstrate that both off- and on-policy methods benefit from this approach through experimental comparison of DQN, DDPG, and TRPO on high-dimensional discrete action environments as well as continuous control tasks. Our results show that RL with parameter noise learns more efficiently than traditional RL with action space noise and evolutionary strategies individually.

Captured tweets and retweets: 1

UCB and InfoGain Exploration via $\boldsymbol{Q}$-Ensembles

Richard Y. Chen, John Schulman, Pieter Abbeel, Szymon Sidor

We show how an ensemble of $Q^*$-functions can be leveraged for more effective exploration in deep reinforcement learning. We build on well established algorithms from the bandit setting, and adapt them to the $Q$-learning setting. First we propose an exploration strategy based on upper-confidence bounds (UCB). Next, we define an ''InfoGain'' exploration bonus, which depends on the disagreement of the $Q$-ensemble. Our experiments show significant gains on the Atari benchmark.

Captured tweets and retweets: 2

Detecting and Explaining Crisis

Rohan Kshirsagar, Robert Morris, Sam Bowman

Individuals on social media may reveal themselves to be in various states of crisis (e.g. suicide, self-harm, abuse, or eating disorders). Detecting crisis from social media text automatically and accurately can have profound consequences. However, detecting a general state of crisis without explaining why has limited applications. An explanation in this context is a coherent, concise subset of the text that rationalizes the crisis detection. We explore several methods to detect and explain crisis using a combination of neural and non-neural techniques. We evaluate these techniques on a unique data set obtained from Koko, an anonymous emotional support network available through various messaging applications. We annotate a small subset of the samples labeled with crisis with corresponding explanations. Our best technique significantly outperforms the baseline for detection and explanation.

Captured tweets and retweets: 13

On-the-fly Operation Batching in Dynamic Computation Graphs

Graham Neubig, Yoav Goldberg, Chris Dyer

Dynamic neural network toolkits such as PyTorch, DyNet, and Chainer offer more flexibility for implementing models that cope with data of varying dimensions and structure, relative to toolkits that operate on statically declared computations (e.g., TensorFlow, CNTK, and Theano). However, existing toolkits - both static and dynamic - require that the developer organize the computations into the batches necessary for exploiting high-performance algorithms and hardware. This batching task is generally difficult, but it becomes a major hurdle as architectures become complex. In this paper, we present an algorithm, and its implementation in the DyNet toolkit, for automatically batching operations. Developers simply write minibatch computations as aggregations of single instance computations, and the batching algorithm seamlessly executes them, on the fly, using computationally efficient batched operations. On a variety of tasks, we obtain throughput similar to that obtained with manual batches, as well as comparable speedups over single-instance learning on architectures that are impractical to batch manually.

Captured tweets and retweets: 2

1 2 3 4 5 6 25 26