Fork me on GitHub

Trending arXiv

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


1 2 24 25 26 27 28 29 30 39 40

From phonemes to images: levels of representation in a recurrent neural model of visually-grounded language learning

Lieke Gelderloos, Grzegorz Chrupała

We present a model of visually-grounded language learning based on stacked gated recurrent neural networks which learns to predict visual features given an image description in the form of a sequence of phonemes. The learning task resembles that faced by human language learners who need to discover both structure and meaning from noisy and ambiguous data across modalities. We show that our model indeed learns to predict features of the visual context given phonetically transcribed image descriptions, and show that it represents linguistic information in a hierarchy of levels: lower layers in the stack are comparatively more sensitive to form, whereas higher layers are more sensitive to meaning.

Captured tweets and retweets: 1

Fully Character-Level Neural Machine Translation without Explicit Segmentation

Jason Lee, Kyunghyun Cho, Thomas Hofmann

Most existing machine translation systems operate at the level of words, relying on explicit segmentation to extract tokens. We introduce a neural machine translation (NMT) model that maps a source character sequence to a target character sequence without any segmentation. We employ a character-level convolutional network with max-pooling at the encoder to reduce the length of source representation, allowing the model to be trained at a speed comparable to subword-level models while capturing local regularities. Our character-to-character model outperforms a recently proposed baseline with a subword-level encoder on WMT'15 DE-EN and CS-EN, and gives comparable performance on FI-EN and RU-EN. We then demonstrate that it is possible to share a single character-level encoder across multiple languages by training a model on a many-to-one translation task. In this multilingual setting, the character-level encoder significantly outperforms the subword-level encoder on all the language pairs. We also observe that the quality of the multilingual character-level translation even surpasses the models trained and tuned on one language pair, namely on CS-EN, FI-EN and RU-EN.

Captured tweets and retweets: 33

Deep Pyramidal Residual Networks

Dongyoon Han, Jiwhan Kim, Junmo Kim

Deep convolutional neural networks (DCNNs) have shown remarkable performance in image classification tasks in recent years. Generally, deep neural network architectures are stacks consisting of a large number of convolution layers, and they perform downsampling along the spatial dimension via pooling to reduce memory usage. At the same time, the feature map dimension (i.e., the number of channels) is sharply increased at downsampling locations, which is essential to ensure effective performance because it increases the capability of high-level attributes. Moreover, this also applies to residual networks and is very closely related to their performance. In this research, instead of using downsampling to achieve a sharp increase at each residual unit, we gradually increase the feature map dimension at all the units to involve as many locations as possible. This is discussed in depth together with our new insights as it has proven to be an effective design to improve the generalization ability. Furthermore, we propose a novel residual unit capable of further improving the classification accuracy with our new network architecture. Experiments on benchmark CIFAR datasets have shown that our network architecture has a superior generalization ability compared to the original residual networks. Code is available at

Captured tweets and retweets: 43

Deep Convolutional Networks as Models of Generalization and Blending Within Visual Creativity

Graeme McCaig, Steve DiPaola, Liane Gabora

We examine two recent artificial intelligence (AI) based deep learning algorithms for visual blending in convolutional neural networks (Mordvintsev et al. 2015, Gatys et al. 2015). To investigate the potential value of these algorithms as tools for computational creativity research, we explain and schematize the essential aspects of the algorithms' operation and give visual examples of their output. We discuss the relationship of the two algorithms to human cognitive science theories of creativity such as conceptual blending theory and honing theory, and characterize the algorithms with respect to generation of novelty and aesthetic quality.

Captured tweets and retweets: 15

Equality of Opportunity in Supervised Learning

Moritz Hardt, Eric Price, Nathan Srebro

We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features. Assuming data about the predictor, target, and membership in the protected group are available, we show how to optimally adjust any learned predictor so as to remove discrimination according to our definition. Our framework also improves incentives by shifting the cost of poor classification from disadvantaged groups to the decision maker, who can respond by improving the classification accuracy. In line with other studies, our notion is oblivious: it depends only on the joint statistics of the predictor, the target and the protected attribute, but not on interpretation of individualfeatures. We study the inherent limits of defining and identifying biases based on such oblivious measures, outlining what can and cannot be inferred from different oblivious tests. We illustrate our notion using a case study of FICO credit scores.

Captured tweets and retweets: 5

Grad-CAM: Why did you say that? Visual Explanations from Deep Networks via Gradient-based Localization

Ramprasaath R. Selvaraju, Abhishek Das, Ramakrishna Vedantam, Michael Cogswell, Devi Parikh, Dhruv Batra

We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing the regions of input that are "important" for predictions from these models - or visual explanations. Our approach, called Gradient-weighted Class Activation Mapping (Grad-CAM), uses the class-specific gradient information flowing into the final convolutional layer of a CNN to produce a coarse localization map of the important regions in the image. Grad-CAM is a strict generalization of the Class Activation Mapping. Unlike CAM, Grad-CAM requires no re-training and is broadly applicable to any CNN-based architectures. We also show how Grad-CAM may be combined with existing pixel-space visualizations to create a high-resolution class-discriminative visualization (Guided Grad-CAM). We generate Grad-CAM and Guided Grad-CAM visual explanations to better understand image classification, image captioning, and visual question answering (VQA) models. In the context of image classification models, our visualizations (a) lend insight into their failure modes showing that seemingly unreasonable predictions have reasonable explanations, and (b) outperform pixel-space gradient visualizations (Guided Backpropagation and Deconvolution) on the ILSVRC-15 weakly supervised localization task. For image captioning and VQA, our visualizations expose the somewhat surprising insight that common CNN + LSTM models can often be good at localizing discriminative input image regions despite not being trained on grounded image-text pairs. Finally, we design and conduct human studies to measure if Guided Grad-CAM explanations help users establish trust in the predictions made by deep networks. Interestingly, we show that Guided Grad-CAM helps untrained users successfully discern a "stronger" deep network from a "weaker" one even when both networks make identical predictions.

Captured tweets and retweets: 4

Deep Learning with Coherent Nanophotonic Circuits

Yichen Shen, Nicholas C. Harris, Scott Skirlo, Mihika Prabhu, Tom Baehr-Jones, Michael Hochberg, Xin Sun, Shijie Zhao, Hugo Larochelle, Dirk Englund, Marin Soljacic

Artificial Neural Networks are computational network models inspired by signal processing in the brain. These models have dramatically improved the performance of many learning tasks, including speech and object recognition. However, today's computing hardware is inefficient at implementing neural networks, in large part because much of it was designed for von Neumann computing schemes. Significant effort has been made to develop electronic architectures tuned to implement artificial neural networks that improve upon both computational speed and energy efficiency. Here, we propose a new architecture for a fully-optical neural network that, using unique advantages of optics, promises a computational speed enhancement of at least two orders of magnitude over the state-of-the-art and three orders of magnitude in power efficiency for conventional learning tasks. We experimentally demonstrate essential parts of our architecture using a programmable nanophotonic processor.

Captured tweets and retweets: 6

Deep Learning with Separable Convolutions

François Chollet

We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the recently introduced "separable convolution" operation. In this light, a separable convolution can be understood as an Inception module with a maximally large number of towers. This observation leads us to propose a novel deep convolutional neural network architecture inspired by Inception, where Inception modules have been replaced with separable convolutions. We show that this architecture, dubbed Xception, slightly outperforms Inception V3 on the ImageNet dataset (which Inception V3 was designed for), and significantly outperforms Inception V3 on a larger image classification dataset comprising 350 million images and 17,000 classes. Since the Xception architecture has the same number of parameter as Inception V3, the performance gains are not due to increased capacity but rather to a more efficient use of model parameters.

Captured tweets and retweets: 6

Optimization of Convolutional Neural Network using Microcanonical Annealing Algorithm

Vina Ayumi, L. M. Rasdi Rere, Mohamad Ivan Fanany, Aniati Murni Arymurthy

Convolutional neural network (CNN) is one of the most prominent architectures and algorithm in Deep Learning. It shows a remarkable improvement in the recognition and classification of objects. This method has also been proven to be very effective in a variety of computer vision and machine learning problems. As in other deep learning, however, training the CNN is interesting yet challenging. Recently, some metaheuristic algorithms have been used to optimize CNN using Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing and Harmony Search. In this paper, another type of metaheuristic algorithms with different strategy has been proposed, i.e. Microcanonical Annealing to optimize Convolutional Neural Network. The performance of the proposed method is tested using the MNIST and CIFAR-10 datasets. Although experiment results of MNIST dataset indicate the increase in computation time (1.02x - 1.38x), nevertheless this proposed method can considerably enhance the performance of the original CNN (up to 4.60\%). On the CIFAR10 dataset, currently, state of the art is 96.53\% using fractional pooling, while this proposed method achieves 99.14\%.

Captured tweets and retweets: 2

Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?

Matthew Johnson-Roberson, Charles Barto, Rounak Mehta, Sharath Nittur Sridhar, Ram Vasudevan

Deep learning has rapidly transformed the state of the art algorithms used to address a variety of problems in computer vision and robotics. These breakthroughs have however relied upon massive amounts of human annotated training data. This time-consuming process has begun impeding the progress of these deep learning efforts. This paper describes a method to incorporate photo-realistic computer images from a simulation engine to rapidly generate annotated data that can be used for training of machine learning algorithms. We demonstrate that a state of the art architecture, which is trained only using these synthetic annotations, performs better than the identical architecture trained on human annotated real-world data, when tested on the KITTI data set for vehicle detection. By training machine learning algorithms on a rich virtual world, this paper illustrates that real objects in real scenes can be learned and classified using synthetic data. This approach offers the possibility of accelerating deep learning's application to sensor based classification problems like those that appear in self-driving cars.

Captured tweets and retweets: 2

Connecting Generative Adversarial Networks and Actor-Critic Methods

David Pfau, Oriol Vinyals

Both generative adversarial networks (GAN) in unsupervised learning and actor-critic methods in reinforcement learning (RL) have gained a reputation for being difficult to optimize. Practitioners in both fields have amassed a large number of strategies to mitigate these instabilities and improve training. Here we show that GANs can be viewed as actor-critic methods in an environment where the actor cannot affect the reward. We review the strategies for stabilizing training for each class of models, both those that generalize between the two and those that are particular to that model. We also review a number of extensions to GANs and RL algorithms with even more complicated information flow. We hope that by highlighting this formal connection we will encourage both GAN and RL communities to develop general, scalable, and stable algorithms for multilevel optimization with deep networks, and to draw inspiration across communities.

Captured tweets and retweets: 15

Understanding intermediate layers using linear classifier probes

Guillaume Alain, Yoshua Bengio

Neural network models have a reputation for being black boxes. We propose a new method to understand better the roles and dynamics of the intermediate layers. This has direct consequences on the design of such models and it enables the expert to be able to justify certain heuristics (such as the auxiliary heads in the Inception model). Our method uses linear classifiers, referred to as "probes", where a probe can only use the hidden units of a given intermediate layer as discriminating features. Moreover, these probes cannot affect the training phase of a model, and they are generally added after training. They allow the user to visualize the state of the model at multiple steps of training. We demonstrate how this can be used to develop a better intuition about a known model and to diagnose potential problems.

Captured tweets and retweets: 3

Visual Question Answering: Datasets, Algorithms, and Future Challenges

Kushal Kafle, Christopher Kanan

Visual Question Answering (VQA) is a recent problem in computer vision and natural language processing that has garnered a large amount of interest from the deep learning, computer vision, and natural language processing communities. In VQA, an algorithm needs to answer text-based questions about images. Since the release of the first VQA dataset in 2014, several additional datasets have been released and many algorithms have been proposed. In this review, we critically examine the current state of VQA in terms of problem formulation, existing datasets, evaluation metrics, and algorithms. In particular, we discuss the limitations of current datasets with regard to their ability to properly train and assess VQA algorithms. We then exhaustively review existing algorithms for VQA. Finally, we discuss possible future directions for VQA and image understanding research.

Captured tweets and retweets: 2

Tutorial on Answering Questions about Images with Deep Learning

Mateusz Malinowski, Mario Fritz

Together with the development of more accurate methods in Computer Vision and Natural Language Understanding, holistic architectures that answer on questions about the content of real-world images have emerged. In this tutorial, we build a neural-based approach to answer questions about images. We base our tutorial on two datasets: (mostly on) DAQUAR, and (a bit on) VQA. With small tweaks the models that we present here can achieve a competitive performance on both datasets, in fact, they are among the best methods that use a combination of LSTM with a global, full frame CNN representation of an image. We hope that after reading this tutorial, the reader will be able to use Deep Learning frameworks, such as Keras and introduced Kraino, to build various architectures that will lead to a further performance improvement on this challenging task.

Captured tweets and retweets: 2

Deep Reinforcement Learning for Robotic Manipulation

Shixiang Gu, Ethan Holly, Timothy Lillicrap, Sergey Levine

Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of the learning process in favor of achieving training times that are practical for real physical systems. This typically involves introducing hand-engineered policy representations and human-supplied demonstrations. Deep reinforcement learning alleviates this limitation by training general-purpose neural network policies, but applications of direct deep reinforcement learning algorithms have so far been restricted to simulated settings and relatively simple tasks, due to their apparent high sample complexity. In this paper, we demonstrate that a recent deep reinforcement learning algorithm based on off-policy training of deep Q-functions can scale to complex 3D manipulation tasks and can learn deep neural network policies efficiently enough to train on real physical robots. We demonstrate that the training times can be further reduced by parallelizing the algorithm across multiple robots which pool their policy updates asynchronously. Our experimental evaluation shows that our method can learn a variety of 3D manipulation skills in simulation and a complex door opening skill on real robots without any prior demonstrations or manually designed representations.

Captured tweets and retweets: 6

Video Pixel Networks

Nal Kalchbrenner, Aaron van den Oord, Karen Simonyan, Ivo Danihelka, Oriol Vinyals, Alex Graves, Koray Kavukcuoglu

We propose a probabilistic video model, the Video Pixel Network (VPN), that estimates the discrete joint distribution of the raw pixel values in a video. The model and the neural architecture reflect the time, space and color structure of video tensors and encode it as a four-dimensional dependency chain. The VPN approaches the best possible performance on the Moving MNIST benchmark, a leap over the previous state of the art, and the generated videos show only minor deviations from the ground truth. The VPN also produces detailed samples on the action-conditional Robotic Pushing benchmark and generalizes to the motion of novel objects.

Captured tweets and retweets: 13

Learning to Translate in Real-time with Neural Machine Translation

Jiatao Gu, Graham Neubig, Kyunghyun Cho, Victor O. K. Li

Translating in real-time, a.k.a. simultaneous translation, outputs translation words before the input sentence ends, which is a challenging problem for conventional machine translation methods. We propose a neural machine translation (NMT) framework for simultaneous translation in which an agent learns to make decisions on when to translate from the interaction with a pre-trained NMT environment. To trade off quality and delay, we extensively explore various targets for delay and design a method for beam-search applicable in the simultaneous MT setting. Experiments against state-of-the-art baselines on two language pairs demonstrate the efficacy of the proposed framework both quantitatively and qualitatively.

Captured tweets and retweets: 8

X-CNN: Cross-modal Convolutional Neural Networks for Sparse Datasets

Petar Veličković, Duo Wang, Nicholas D. Lane, Pietro Liò

In this paper we propose cross-modal convolutional neural networks (X-CNNs), a novel biologically inspired type of CNN architectures, treating gradient descent-specialised CNNs as individual units of processing in a larger-scale network topology, while allowing for unconstrained information flow and/or weight sharing between analogous hidden layers of the network---thus generalising the already well-established concept of neural network ensembles (where information typically may flow only between the output layers of the individual networks). The constituent networks are individually designed to learn the output function on their own subset of the input data, after which cross-connections between them are introduced after each pooling operation to periodically allow for information exchange between them. This injection of knowledge into a model (by prior partition of the input data through domain knowledge or unsupervised methods) is expected to yield greatest returns in sparse data environments, which are typically less suitable for training CNNs. For evaluation purposes, we have compared a standard four-layer CNN as well as a sophisticated FitNet4 architecture against their cross-modal variants on the CIFAR-10 and CIFAR-100 datasets with differing percentages of the training data being removed, and find that at lower levels of data availability, the X-CNNs significantly outperform their baselines (typically providing a 2--6% benefit, depending on the dataset size and whether data augmentation is used), while still maintaining an edge on all of the full dataset tests.

Captured tweets and retweets: 6

Structured Inference Networks for Nonlinear State Space Models

Rahul G. Krishnan, Uri Shalit, David Sontag

Gaussian state space models have been used for decades as generative models of sequential data. They admit an intuitive probabilistic interpretation, have a simple functional form, and enjoy widespread adoption. We introduce a unified algorithm to efficiently learn a broad class of linear and non-linear state space models, including variants where the emission and transition distributions are modeled by deep neural networks. Our learning algorithm simultaneously learns a compiled inference network and the generative model, leveraging a structured variational approximation parameterized by recurrent neural networks to mimic the posterior distribution. We apply the learning algorithm to both synthetic and real-world datasets, demonstrating its scalability and versatility. We find that using the structured approximation to the posterior results in models with significantly higher held-out likelihood.

Captured tweets and retweets: 1

Semantic Parsing with Semi-Supervised Sequential Autoencoders

Tomáš Kočiský, Gábor Melis, Edward Grefenstette, Chris Dyer, Wang Ling, Phil Blunsom, Karl Moritz Hermann

We present a novel semi-supervised approach for sequence transduction and apply it to semantic parsing. The unsupervised component is based on a generative model in which latent sentences generate the unpaired logical forms. We apply this method to a number of semantic parsing tasks focusing on domains with limited access to labelled training data and extend those datasets with synthetically generated logical forms.

Captured tweets and retweets: 4

1 2 24 25 26 27 28 29 30 39 40