January 28, 2020

2770 words 14 mins read

Paper Group ANR 926

Towards Brain-inspired System: Deep Recurrent Reinforcement Learning for Simulated Self-driving Agent. An Empirical Study of the Relationships between Code Readability and Software Complexity. A Dual Memory Structure for Efficient Use of Replay Memory in Deep Reinforcement Learning. Optimistic Adaptive Acceleration for Optimization. Generic Varianc …

Towards Brain-inspired System: Deep Recurrent Reinforcement Learning for Simulated Self-driving Agent


Title	Towards Brain-inspired System: Deep Recurrent Reinforcement Learning for Simulated Self-driving Agent
Authors	Jieneng Chen, Jingye Chen, Ruiming Zhang, Xiaobin Hu
Abstract	An effective way to achieve intelligence is to simulate various intelligent behaviors in the human brain. In recent years, bio-inspired learning methods have emerged, and they are different from the classical mathematical programming principle. In the perspective of brain inspiration, reinforcement learning has gained additional interest in solving decision-making tasks as increasing neuroscientific research demonstrates that significant links exist between reinforcement learning and specific neural substrates. Because of the tremendous research that focuses on human brains and reinforcement learning, scientists have investigated how robots can autonomously tackle complex tasks in the form of a self-driving agent control in a human-like way. In this study, we propose an end-to-end architecture using novel deep-Q-network architecture in conjunction with a recurrence to resolve the problem in the field of simulated self-driving. The main contribution of this study is that we trained the driving agent using a brain-inspired trial-and-error technique, which was in line with the real world situation. Besides, there are three innovations in the proposed learning network: raw screen outputs are the only information which the driving agent can rely on, a weighted layer that enhances the differences of the lengthy episode, and a modified replay mechanism that overcomes the problem of sparsity and accelerates learning. The proposed network was trained and tested under a third-partied OpenAI Gym environment. After training for several episodes, the resulting driving agent performed advanced behaviors in the given scene. We hope that in the future, the proposed brain-inspired learning system would inspire practicable self-driving control solutions.
Tasks	Decision Making
Published	2019-03-29
URL	http://arxiv.org/abs/1903.12517v1
PDF	http://arxiv.org/pdf/1903.12517v1.pdf
PWC	https://paperswithcode.com/paper/towards-brain-inspired-system-deep-recurrent
Repo
Framework

An Empirical Study of the Relationships between Code Readability and Software Complexity


Title	An Empirical Study of the Relationships between Code Readability and Software Complexity
Authors	Duaa Alawad, Manisha Panta, Minhaz Zibran, Md Rakibul Islam
Abstract	Code readability and software complexity are important software quality metrics that impact other software metrics such as maintainability, reusability, portability and reliability. This paper presents an empirical study of the relationships between code readability and program complexity. The results are derived from an analysis of 35 Java programs that cover 23 distinct code constructs. The analysis includes six readability metrics and two complexity metrics. Our study empirically confirms the existing wisdom that readability and complexity are negatively correlated. Applying a machine learning technique, we also identify and rank those code constructs that substantially affect code readability.
Tasks
Published	2019-08-30
URL	https://arxiv.org/abs/1909.01760v1
PDF	https://arxiv.org/pdf/1909.01760v1.pdf
PWC	https://paperswithcode.com/paper/an-empirical-study-of-the-relationships
Repo
Framework

A Dual Memory Structure for Efficient Use of Replay Memory in Deep Reinforcement Learning


Title	A Dual Memory Structure for Efficient Use of Replay Memory in Deep Reinforcement Learning
Authors	Wonshick Ko, Dong Eui Chang
Abstract	In this paper, we propose a dual memory structure for reinforcement learning algorithms with replay memory. The dual memory consists of a main memory that stores various data and a cache memory that manages the data and trains the reinforcement learning agent efficiently. Experimental results show that the dual memory structure achieves higher training and test scores than the conventional single memory structure in three selected environments of OpenAI Gym. This implies that the dual memory structure enables better and more efficient training than the single memory structure.
Tasks
Published	2019-07-15
URL	https://arxiv.org/abs/1907.06396v1
PDF	https://arxiv.org/pdf/1907.06396v1.pdf
PWC	https://paperswithcode.com/paper/a-dual-memory-structure-for-efficient-use-of
Repo
Framework

Optimistic Adaptive Acceleration for Optimization


Title	Optimistic Adaptive Acceleration for Optimization
Authors	Jun-Kun Wang, Xiaoyun Li, Ping Li
Abstract	AMSGrad is a popular adaptive gradient based optimization algorithm that is widely used in training deep neural networks. The new variant assumes that minibatch gradients in consecutive iterations have some underlying structure, which makes the gradients sequentially predictable. By exploiting the predictability and some ideas from Optimistic Online learning, the proposed algorithm can accelerate the convergence and also enjoys a tighter regret bound. We evaluate Optimistic-AMSGrad and AMSGrad in terms of various performance measures (i.e., training loss, testing loss, and classification accuracy on training/testing data), which demonstrate that Optimistic-AMSGrad improves AMSGrad.
Tasks
Published	2019-03-04
URL	https://arxiv.org/abs/1903.01435v2
PDF	https://arxiv.org/pdf/1903.01435v2.pdf
PWC	https://paperswithcode.com/paper/optimistic-adaptive-acceleration-for
Repo
Framework

Generic Variance Bounds on Estimation and Prediction Errors in Time Series Analysis: An Entropy Perspective


Title	Generic Variance Bounds on Estimation and Prediction Errors in Time Series Analysis: An Entropy Perspective
Authors	Song Fang, Mikael Skoglund, Karl Henrik Johansson, Hideaki Ishii, Quanyan Zhu
Abstract	In this paper, we obtain generic bounds on the variances of estimation and prediction errors in time series analysis via an information-theoretic approach. It is seen in general that the error bounds are determined by the conditional entropy of the data point to be estimated or predicted given the side information or past observations. Additionally, we discover that in order to achieve the prediction error bounds asymptotically, the necessary and sufficient condition is that the “innovation” is asymptotically white Gaussian. When restricted to Gaussian processes and 1-step prediction, our bounds are shown to reduce to the Kolmogorov-Szeg"o formula and Wiener-Masani formula known from linear prediction theory.
Tasks	Gaussian Processes, Time Series, Time Series Analysis
Published	2019-04-09
URL	https://arxiv.org/abs/1904.04765v4
PDF	https://arxiv.org/pdf/1904.04765v4.pdf
PWC	https://paperswithcode.com/paper/generic-variance-bounds-on-estimation-and
Repo
Framework

Specializing Word Embeddings (for Parsing) by Information Bottleneck


Title	Specializing Word Embeddings (for Parsing) by Information Bottleneck
Authors	Xiang Lisa Li, Jason Eisner
Abstract	Pre-trained word embeddings like ELMo and BERT contain rich syntactic and semantic information, resulting in state-of-the-art performance on various tasks. We propose a very fast variational information bottleneck (VIB) method to nonlinearly compress these embeddings, keeping only the information that helps a discriminative parser. We compress each word embedding to either a discrete tag or a continuous vector. In the discrete version, our automatically compressed tags form an alternative tag set: we show experimentally that our tags capture most of the information in traditional POS tag annotations, but our tag sequences can be parsed more accurately at the same level of tag granularity. In the continuous version, we show experimentally that moderately compressing the word embeddings by our method yields a more accurate parser in 8 of 9 languages, unlike simple dimensionality reduction.
Tasks	Dimensionality Reduction, Word Embeddings
Published	2019-10-01
URL	https://arxiv.org/abs/1910.00163v1
PDF	https://arxiv.org/pdf/1910.00163v1.pdf
PWC	https://paperswithcode.com/paper/specializing-word-embeddings-for-parsing-by
Repo
Framework

Computational and Robotic Models of Early Language Development: A Review


Title	Computational and Robotic Models of Early Language Development: A Review
Authors	Pierre-Yves Oudeyer, George Kachergis, William Schueller
Abstract	We review computational and robotics models of early language learning and development. We first explain why and how these models are used to understand better how children learn language. We argue that they provide concrete theories of language learning as a complex dynamic system, complementing traditional methods in psychology and linguistics. We review different modeling formalisms, grounded in techniques from machine learning and artificial intelligence such as Bayesian and neural network approaches. We then discuss their role in understanding several key mechanisms of language development: cross-situational statistical learning, embodiment, situated social interaction, intrinsically motivated learning, and cultural evolution. We conclude by discussing future challenges for research, including modeling of large-scale empirical data about language acquisition in real-world environments. Keywords: Early language learning, Computational and robotic models, machine learning, development, embodiment, social interaction, intrinsic motivation, self-organization, dynamical systems, complexity.
Tasks	Language Acquisition
Published	2019-03-25
URL	http://arxiv.org/abs/1903.10246v1
PDF	http://arxiv.org/pdf/1903.10246v1.pdf
PWC	https://paperswithcode.com/paper/computational-and-robotic-models-of-early
Repo
Framework

Back to the Future: Knowledge Distillation for Human Action Anticipation


Title	Back to the Future: Knowledge Distillation for Human Action Anticipation
Authors	Vinh Tran, Yang Wang, Minh Hoai
Abstract	We consider the task of training a neural network to anticipate human actions in video. This task is challenging given the complexity of video data, the stochastic nature of the future, and the limited amount of annotated training data. In this paper, we propose a novel knowledge distillation framework that uses an action recognition network to supervise the training of an action anticipation network, guiding the latter to attend to the relevant information needed for correctly anticipating the future actions. This framework is possible thanks to a novel loss function to account for positional shifts of semantic concepts in a dynamic video. The knowledge distillation framework is a form of self-supervised learning, and it takes advantage of unlabeled data. Experimental results on JHMDB and EPIC-KITCHENS dataset show the effectiveness of our approach.
Tasks	Temporal Action Localization
Published	2019-04-09
URL	http://arxiv.org/abs/1904.04868v1
PDF	http://arxiv.org/pdf/1904.04868v1.pdf
PWC	https://paperswithcode.com/paper/back-to-the-future-knowledge-distillation-for
Repo
Framework

Automatic Video Colorization using 3D Conditional Generative Adversarial Networks


Title	Automatic Video Colorization using 3D Conditional Generative Adversarial Networks
Authors	Panagiotis Kouzouglidis, Giorgos Sfikas, Christophoros Nikou
Abstract	In this work, we present a method for automatic colorization of grayscale videos. The core of the method is a Generative Adversarial Network that is trained and tested on sequences of frames in a sliding window manner. Network convolutional and deconvolutional layers are three-dimensional, with frame height, width and time as the dimensions taken into account. Multiple chrominance estimates per frame are aggregated and combined with available luminance information to recreate a colored sequence. Colorization trials are run succesfully on a dataset of old black-and-white films. The usefulness of our method is also validated with numerical results, computed with a newly proposed metric that measures colorization consistency over a frame sequence.
Tasks	Colorization
Published	2019-05-08
URL	https://arxiv.org/abs/1905.03023v1
PDF	https://arxiv.org/pdf/1905.03023v1.pdf
PWC	https://paperswithcode.com/paper/automatic-video-colorization-using-3d
Repo
Framework

Robust Assessment of Real-World Adversarial Examples


Title	Robust Assessment of Real-World Adversarial Examples
Authors	Brett Jefferson, Carlos Ortiz Marrero
Abstract	We explore rigorous, systematic, and controlled experimental evaluation of adversarial examples in the real world and propose a testing regimen for evaluation of real world adversarial objects. We show that for small scene/ environmental perturbations, large adversarial performance differences exist. Current state of adversarial reporting exists largely as a frequency count over a dynamic collections of scenes. Our work underscores the need for either a more complete report or a score that incorporates scene changes and baseline performance for models and environments tested by adversarial developers. We put forth a score that attempts to address the above issues in a straight-forward exemplar application for multiple generated adversary examples. We contribute the following: 1. a testbed for adversarial assessment, 2. a score for adversarial examples, and 3. a collection of additional evaluations on testbed data.
Tasks
Published	2019-11-24
URL	https://arxiv.org/abs/1911.10435v2
PDF	https://arxiv.org/pdf/1911.10435v2.pdf
PWC	https://paperswithcode.com/paper/robustness-metrics-for-real-world-adversarial
Repo
Framework

Unsupervised Segmentation Algorithms’ Implementation in ITK for Tissue Classification via Human Head MRI Scans


Title	Unsupervised Segmentation Algorithms’ Implementation in ITK for Tissue Classification via Human Head MRI Scans
Authors	Shadman Sakib, Md. Abu Bakr Siddique
Abstract	Tissue classification is one of the significant tasks in the field of biomedical image analysis. Magnetic Resonance Imaging (MRI) is of great importance in tissue classification especially in the areas of brain tissue classification which is able to recognize anatomical areas of interest such as surgical planning, monitoring therapy, clinical drug trials, image registration, stereotactic neurosurgery, radiotherapy etc. The task of this paper is to implement different unsupervised classification algorithms in ITK and perform tissue classification (white matter, gray matter, cerebrospinal fluid (CSF) and background of the human brain). For this purpose, 5 grayscale head MRI scans are provided. In order of classifying brain tissues, three algorithms are used. These are: Otsu thresholding, Bayesian classification and Bayesian classification with Gaussian smoothing. The obtained classification results are analyzed in the results and discussion section.
Tasks	Image Registration
Published	2019-02-26
URL	https://arxiv.org/abs/1902.11131v4
PDF	https://arxiv.org/pdf/1902.11131v4.pdf
PWC	https://paperswithcode.com/paper/unsupervised-segmentation-algorithms
Repo
Framework

Encoding Visual Attributes in Capsules for Explainable Medical Diagnoses


Title	Encoding Visual Attributes in Capsules for Explainable Medical Diagnoses
Authors	Rodney LaLonde, Drew Torigian, Ulas Bagci
Abstract	In high-risk domains, understanding the reasons behind machine-generated predictions is vital in assessing trust. In this study, we introduce a novel design of multi-task capsule network to provide explainable medical image-based diagnosis. Our proposed explainable capsule architecture, called X-Caps, encodes high-level visual attributes within the vectors of its capsules, then forms predictions based on these interpretable features. Since these attributes are independent, we modify the dynamic routing algorithm to independently route information from child capsules to parents. To increase the explainability of our method further, we propose to train our network on a distribution of expert labels directly, rather than the average of these labels as done in previous studies. This provides a meaningful metric of model confidence, punishing over/under confidence, directly supervised by human-experts’ agreement. In our example high-risk application of lung cancer diagnosis, we conduct experiments on a large and diverse dataset of over 1000 CT scans, where our proposed X-Caps, a relatively small 2D capsule network, significantly outperforms the previous state-of-the-art deep dual-path dense 3D CNN in predicting visual attribute scores while also improving diagnostic accuracy. To the best of our knowledge, this is the first study to investigate capsule networks for making predictions based on human-level interpretable visual attributes in general and its applications to explainable medical image diagnosis in particular.
Tasks	Lung Cancer Diagnosis, Multi-Task Learning
Published	2019-09-12
URL	https://arxiv.org/abs/1909.05926v2
PDF	https://arxiv.org/pdf/1909.05926v2.pdf
PWC	https://paperswithcode.com/paper/encoding-high-level-visual-attributes-in
Repo
Framework

Interpretable ICD Code Embeddings with Self- and Mutual-Attention Mechanisms


Title	Interpretable ICD Code Embeddings with Self- and Mutual-Attention Mechanisms
Authors	Dixin Luo, Hongteng Xu, Lawrence Carin
Abstract	We propose a novel and interpretable embedding method to represent the international statistical classification codes of diseases and related health problems (i.e., ICD codes). This method considers a self-attention mechanism within the disease domain and a mutual-attention mechanism jointly between diseases and procedures. This framework captures the clinical relationships between the disease codes and procedures associated with hospital admissions, and it predicts procedures according to diagnosed diseases. A self-attention network is learned to fuse the embeddings of the diseases for each admission. The similarities between the fused disease embedding and the procedure embeddings indicate which procedure should potentially be recommended. Additionally, when learning the embeddings of the ICD codes, the optimal transport between the diseases and the procedures within each admission is calculated as a regularizer of the embeddings. The optimal transport provides a mutual-attention map between diseases and the procedures, which suppresses the ambiguity within their clinical relationships. The proposed method achieves clinically-interpretable embeddings of ICD codes, and outperforms state-of-the-art embedding methods in procedure recommendation.
Tasks
Published	2019-06-13
URL	https://arxiv.org/abs/1906.05492v1
PDF	https://arxiv.org/pdf/1906.05492v1.pdf
PWC	https://paperswithcode.com/paper/interpretable-icd-code-embeddings-with-self
Repo
Framework

Towards Data-Driven Automatic Video Editing


Title	Towards Data-Driven Automatic Video Editing
Authors	Sergey Podlesnyy
Abstract	Automatic video editing involving at least the steps of selecting the most valuable footage from points of view of visual quality and the importance of action filmed; and cutting the footage into a brief and coherent visual story that would be interesting to watch is implemented in a purely data-driven manner. Visual semantic and aesthetic features are extracted by the ImageNet-trained convolutional neural network, and the editing controller is trained by an imitation learning algorithm. As a result, at test time the controller shows the signs of observing basic cinematography editing rules learned from the corpus of motion pictures masterpieces.
Tasks	Imitation Learning
Published	2019-07-17
URL	https://arxiv.org/abs/1907.07345v1
PDF	https://arxiv.org/pdf/1907.07345v1.pdf
PWC	https://paperswithcode.com/paper/towards-data-driven-automatic-video-editing
Repo
Framework

Reducing Sentiment Bias in Language Models via Counterfactual Evaluation


Title	Reducing Sentiment Bias in Language Models via Counterfactual Evaluation
Authors	Po-Sen Huang, Huan Zhang, Ray Jiang, Robert Stanforth, Johannes Welbl, Jack Rae, Vishal Maini, Dani Yogatama, Pushmeet Kohli
Abstract	Recent improvements in large-scale language models have driven progress on automatic generation of syntactically and semantically consistent text for many real-world applications. Many of these advances leverage the availability of large corpora. While training on such corpora encourages the model to understand long-range dependencies in text, it can also result in the models internalizing the social biases present in the corpora. This paper aims to quantify and reduce biases exhibited by language models. Given a conditioning context (e.g. a writing prompt) and a language model, we analyze if (and how) the sentiment of the generated text is affected by changes in values of sensitive attributes (e.g. country names, occupations, genders, etc.) in the conditioning context, a.k.a. counterfactual evaluation. We quantify these biases by adapting individual and group fairness metrics from the fair machine learning literature. Extensive evaluation on two different corpora (news articles and Wikipedia) shows that state-of-the-art Transformer-based language models exhibit biases learned from data. We propose embedding-similarity and sentiment-similarity regularization methods that improve both individual and group fairness metrics without sacrificing perplexity and semantic similarity—a positive step toward development and deployment of fairer language models for real-world applications.
Tasks	Language Modelling, Semantic Similarity, Semantic Textual Similarity
Published	2019-11-08
URL	https://arxiv.org/abs/1911.03064v1
PDF	https://arxiv.org/pdf/1911.03064v1.pdf
PWC	https://paperswithcode.com/paper/reducing-sentiment-bias-in-language-models-1
Repo
Framework