Paper Group ANR 1724
Online Adaptation through Meta-Learning for Stereo Depth Estimation. Towards Learning How to Properly Play UNO with the iCub Robot. A Neural Network Detector for Spectrum Sensing under Uncertainties. Multiagent Rollout Algorithms and Reinforcement Learning. Object Exchangeability in Reinforcement Learning: Extended Abstract. Combining Machine Learn …
Online Adaptation through Meta-Learning for Stereo Depth Estimation
| Title | Online Adaptation through Meta-Learning for Stereo Depth Estimation |
| Authors | Zhenyu Zhang, Stéphane Lathuilière, Andrea Pilzer, Nicu Sebe, Elisa Ricci, Jian Yang |
| Abstract | In this work, we tackle the problem of online adaptation for stereo depth estimation, that consists in continuously adapting a deep network to a target video recordedin an environment different from that of the source training set. To address this problem, we propose a novel Online Meta-Learning model with Adaption (OMLA). Our proposal is based on two main contributions. First, to reducethe domain-shift between source and target feature distributions we introduce an online feature alignment procedurederived from Batch Normalization. Second, we devise a meta-learning approach that exploits feature alignment forfaster convergence in an online learning setting. Additionally, we propose a meta-pre-training algorithm in order toobtain initial network weights on the source dataset whichfacilitate adaptation on future data streams. Experimentally, we show that both OMLA and meta-pre-training helpthe model to adapt faster to a new environment. Our proposal is evaluated on the wellestablished KITTI dataset,where we show that our online method is competitive withstate of the art algorithms trained in a batch setting. |
| Tasks | Depth Estimation, Meta-Learning, Stereo Depth Estimation |
| Published | 2019-04-17 |
| URL | http://arxiv.org/abs/1904.08462v1 |
| http://arxiv.org/pdf/1904.08462v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-adaptation-through-meta-learning-for |
| Repo | |
| Framework | |
Towards Learning How to Properly Play UNO with the iCub Robot
| Title | Towards Learning How to Properly Play UNO with the iCub Robot |
| Authors | Pablo Barros, Stefan Wermter, Alessandra Sciutti |
| Abstract | While interacting with another person, our reactions and behavior are much affected by the emotional changes within the temporal context of the interaction. Our intrinsic affective appraisal comprising perception, self-assessment, and the affective memories with similar social experiences will drive specific, and in most cases addressed as proper, reactions within the interaction. This paper proposes the roadmap for the development of multimodal research which aims to empower a robot with the capability to provide proper social responses in a Human-Robot Interaction (HRI) scenario. |
| Tasks | |
| Published | 2019-08-02 |
| URL | https://arxiv.org/abs/1908.00744v1 |
| https://arxiv.org/pdf/1908.00744v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-learning-how-to-properly-play-uno |
| Repo | |
| Framework | |
A Neural Network Detector for Spectrum Sensing under Uncertainties
| Title | A Neural Network Detector for Spectrum Sensing under Uncertainties |
| Authors | Ziyu Ye, Qihang Peng, Kelly Levick, Hui Rong, Andrew Gilman, Pamela Cosman, Larry Milstein |
| Abstract | Spectrum sensing is of critical importance in any cognitive radio system. When the primary user’s signal has uncertain parameters, the likelihood ratio test, which is the theoretically optimal detector, generally has no closed-form expression. As a result, spectrum sensing under parameter uncertainty remains an open question, though many detectors exploiting specific features of a primary signal have been proposed and have achieved reasonably good performance. In this paper, a neural network is trained as a detector for modulated signals. The result shows by training on an appropriate dataset, the neural network gains robustness under uncertainties in system parameters including the carrier frequency offset, carrier phase offset, and symbol time offset. The result displays the neural network’s potential in exploiting implicit and incomplete knowledge about the signal’s structure. |
| Tasks | |
| Published | 2019-07-15 |
| URL | https://arxiv.org/abs/1907.07326v2 |
| https://arxiv.org/pdf/1907.07326v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-neural-network-detector-for-spectrum |
| Repo | |
| Framework | |
Multiagent Rollout Algorithms and Reinforcement Learning
| Title | Multiagent Rollout Algorithms and Reinforcement Learning |
| Authors | Dimitri Bertsekas |
| Abstract | We consider finite and infinite horizon dynamic programming problems, where the control at each stage consists of several distinct decisions, each one made by one of several agents. We introduce an algorithm, whereby at every stage, each agent’s decision is made by executing a local rollout algorithm that uses a base policy, together with some coordinating information from the other agents. The amount of local computation required at every stage by each agent is independent of the number of agents, while the amount of global computation (over all agents) grows linearly with the number of agents. By contrast, with the standard rollout algorithm, the amount of global computation grows exponentially with the number of agents. Despite the drastic reduction in required computation, we show that our algorithm has the fundamental cost improvement property of rollout: an improved performance relative to the base policy. We also explore related reinforcement learning and approximate policy iteration algorithms, and we discuss how this cost improvement property is affected when we attempt to improve further the method’s computational efficiency through parallelization of the agents’ computations. |
| Tasks | |
| Published | 2019-09-30 |
| URL | https://arxiv.org/abs/1910.00120v2 |
| https://arxiv.org/pdf/1910.00120v2.pdf | |
| PWC | https://paperswithcode.com/paper/multiagent-rollout-algorithms-and |
| Repo | |
| Framework | |
Object Exchangeability in Reinforcement Learning: Extended Abstract
| Title | Object Exchangeability in Reinforcement Learning: Extended Abstract |
| Authors | John Mern, Dorsa Sadigh, Mykel Kochenderfer |
| Abstract | Although deep reinforcement learning has advanced significantly over the past several years, sample efficiency remains a major challenge. Careful choice of input representations can help improve efficiency depending on the structure present in the problem. In this work, we present an attention-based method to project inputs into an efficient representation space that is invariant under changes to input ordering. We show that our proposed representation results in a search space that is a factor of m! smaller for inputs of m objects. Our experiments demonstrate improvements in sample efficiency for policy gradient methods on a variety of tasks. We show that our representation allows us to solve problems that are otherwise intractable when using naive approaches. |
| Tasks | Policy Gradient Methods |
| Published | 2019-05-07 |
| URL | https://arxiv.org/abs/1905.02698v1 |
| https://arxiv.org/pdf/1905.02698v1.pdf | |
| PWC | https://paperswithcode.com/paper/object-exchangeability-in-reinforcement |
| Repo | |
| Framework | |
Combining Machine Learning and Social Network Analysis to Reveal the Organizational Structures
| Title | Combining Machine Learning and Social Network Analysis to Reveal the Organizational Structures |
| Authors | Mateusz Nurek, Radosław Michalski |
| Abstract | Formation of a hierarchy within an organization is a natural way of optimizing the duties, responsibilities and flow of information. Only for the smallest organizations the lack of the hierarchy is possible, yet, if they grow, its appearance is inevitable. Most often, its existence results in a different nature of the tasks and duties of its members located at different organizational levels. On the other hand, employees often send dozens of emails each day, and by doing so, and also by being engaged in other activities, they naturally form an informal social network where nodes are individuals and edges are the actions linking them. At first, such a social network may seem distinct from the organizational one. However, the analysis of this network may lead to reproducing the organizational hierarchy of companies. This is due to the fact that that people holding a similar position in the hierarchy can possibly share also a similar way of behaving and communicating attributed to their role. The key concept of this work is to evaluate how well social network measures when combined with other features gained from the feature engineering align with the classification of the members of organizational social network. As a technique for answering the research question, machine learning apparatus was employed. Here, for the classification task, Decision Tree and Random Forest algorithms where used, as well as a simple collective classification algorithm, which is also proposed in this paper. The used approach allowed to compare how traditional methods of machine learning classification, while supported by social network analysis, performed in comparison to a typical graph algorithm. |
| Tasks | Feature Engineering |
| Published | 2019-06-23 |
| URL | https://arxiv.org/abs/1906.09576v1 |
| https://arxiv.org/pdf/1906.09576v1.pdf | |
| PWC | https://paperswithcode.com/paper/combining-machine-learning-and-social-network |
| Repo | |
| Framework | |
Wider Networks Learn Better Features
| Title | Wider Networks Learn Better Features |
| Authors | Dar Gilboa, Guy Gur-Ari |
| Abstract | Transferability of learned features between tasks can massively reduce the cost of training a neural network on a novel task. We investigate the effect of network width on learned features using activation atlases — a visualization technique that captures features the entire hidden state responds to, as opposed to individual neurons alone. We find that, while individual neurons do not learn interpretable features in wide networks, groups of neurons do. In addition, the hidden state of a wide network contains more information about the inputs than that of a narrow network trained to the same test accuracy. Inspired by this observation, we show that when fine-tuning the last layer of a network on a new task, performance improves significantly as the width of the network is increased, even though test accuracy on the original task is independent of width. |
| Tasks | |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11572v1 |
| https://arxiv.org/pdf/1909.11572v1.pdf | |
| PWC | https://paperswithcode.com/paper/wider-networks-learn-better-features |
| Repo | |
| Framework | |
mRMR-DNN with Transfer Learning for IntelligentFault Diagnosis of Rotating Machines
| Title | mRMR-DNN with Transfer Learning for IntelligentFault Diagnosis of Rotating Machines |
| Authors | Vikas Singh, Nishchal K. Verma |
| Abstract | In recent years, intelligent condition-based monitoring of rotary machinery systems has become a major research focus of machine fault diagnosis. In condition-based monitoring, it is challenging to form a large-scale well-annotated dataset due to the expense of data acquisition and costly annotation. Along with that, the generated data have a large number of redundant features which degraded the performance of the machine learning models. To overcome this, we have utilized the advantages of minimum redundancy maximum relevance (mRMR) and transfer learning with deep learning model. In this work, mRMR is combined with deep learning and deep transfer learning framework to improve the fault diagnostics performance in term of accuracy and computational complexity. The mRMR reduces the redundant information from data and increases the deep learning performance, whereas transfer learning, reduces a large amount of data dependency for training the model. In the proposed work, two frameworks, i.e., mRMR with deep learning and mRMR with deep transfer learning, have explored and validated on CWRU and IMS rolling element bearings datasets. The analysis shows that the proposed frameworks are able to obtain better diagnostic accuracy in comparison of existing methods and also able to handle the data with a large number of features more quickly. |
| Tasks | Transfer Learning |
| Published | 2019-12-24 |
| URL | https://arxiv.org/abs/1912.11235v2 |
| https://arxiv.org/pdf/1912.11235v2.pdf | |
| PWC | https://paperswithcode.com/paper/mrmr-dnn-with-transfer-learning-for |
| Repo | |
| Framework | |
Sequence Generation: From Both Sides to the Middle
| Title | Sequence Generation: From Both Sides to the Middle |
| Authors | Long Zhou, Jiajun Zhang, Chengqing Zong, Heng Yu |
| Abstract | The encoder-decoder framework has achieved promising process for many sequence generation tasks, such as neural machine translation and text summarization. Such a framework usually generates a sequence token by token from left to right, hence (1) this autoregressive decoding procedure is time-consuming when the output sentence becomes longer, and (2) it lacks the guidance of future context which is crucial to avoid under translation. To alleviate these issues, we propose a synchronous bidirectional sequence generation (SBSG) model which predicts its outputs from both sides to the middle simultaneously. In the SBSG model, we enable the left-to-right (L2R) and right-to-left (R2L) generation to help and interact with each other by leveraging interactive bidirectional attention network. Experiments on neural machine translation (En-De, Ch-En, and En-Ro) and text summarization tasks show that the proposed model significantly speeds up decoding while improving the generation quality compared to the autoregressive Transformer. |
| Tasks | Machine Translation, Text Summarization |
| Published | 2019-06-23 |
| URL | https://arxiv.org/abs/1906.09601v1 |
| https://arxiv.org/pdf/1906.09601v1.pdf | |
| PWC | https://paperswithcode.com/paper/sequence-generation-from-both-sides-to-the |
| Repo | |
| Framework | |
Keeping Notes: Conditional Natural Language Generation with a Scratchpad Mechanism
| Title | Keeping Notes: Conditional Natural Language Generation with a Scratchpad Mechanism |
| Authors | Ryan Y. Benmalek, Madian Khabsa, Suma Desu, Claire Cardie, Michele Banko |
| Abstract | We introduce the Scratchpad Mechanism, a novel addition to the sequence-to-sequence (seq2seq) neural network architecture and demonstrate its effectiveness in improving the overall fluency of seq2seq models for natural language generation tasks. By enabling the decoder at each time step to write to all of the encoder output layers, Scratchpad can employ the encoder as a “scratchpad” memory to keep track of what has been generated so far and thereby guide future generation. We evaluate Scratchpad in the context of three well-studied natural language generation tasks — Machine Translation, Question Generation, and Text Summarization — and obtain state-of-the-art or comparable performance on standard datasets for each task. Qualitative assessments in the form of human judgements (question generation), attention visualization (MT), and sample output (summarization) provide further evidence of the ability of Scratchpad to generate fluent and expressive output. |
| Tasks | Machine Translation, Question Generation, Text Generation, Text Summarization |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.05275v2 |
| https://arxiv.org/pdf/1906.05275v2.pdf | |
| PWC | https://paperswithcode.com/paper/keeping-notes-conditional-natural-language |
| Repo | |
| Framework | |
AIBA: An AI Model for Behavior Arbitration in Autonomous Driving
| Title | AIBA: An AI Model for Behavior Arbitration in Autonomous Driving |
| Authors | Bogdan Trasnea, Claudiu Pozna, Sorin Grigorescu |
| Abstract | Driving in dynamically changing traffic is a highly challenging task for autonomous vehicles, especially in crowded urban roadways. The Artificial Intelligence (AI) system of a driverless car must be able to arbitrate between different driving strategies in order to properly plan the car’s path, based on an understandable traffic scene model. In this paper, an AI behavior arbitration algorithm for Autonomous Driving (AD) is proposed. The method, coined AIBA (AI Behavior Arbitration), has been developed in two stages: (i) human driving scene description and understanding and (ii) formal modelling. The description of the scene is achieved by mimicking a human cognition model, while the modelling part is based on a formal representation which approximates the human driver understanding process. The advantage of the formal representation is that the functional safety of the system can be analytically inferred. The performance of the algorithm has been evaluated in Virtual Test Drive (VTD), a comprehensive traffic simulator, and in GridSim, a vehicle kinematics engine for prototypes. |
| Tasks | Autonomous Driving, Autonomous Vehicles |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09418v2 |
| https://arxiv.org/pdf/1909.09418v2.pdf | |
| PWC | https://paperswithcode.com/paper/aiba-an-ai-model-for-behavior-arbitration-in |
| Repo | |
| Framework | |
Ask Not What AI Can Do, But What AI Should Do: Towards a Framework of Task Delegability
| Title | Ask Not What AI Can Do, But What AI Should Do: Towards a Framework of Task Delegability |
| Authors | Brian Lubars, Chenhao Tan |
| Abstract | While artificial intelligence (AI) holds promise for addressing societal challenges, issues of exactly which tasks to automate and to what extent to do so remain understudied. We approach this problem of task delegability from a human-centered perspective by developing a framework on human perception of task delegation to AI. We consider four high-level factors that can contribute to a delegation decision: motivation, difficulty, risk, and trust. To obtain an empirical understanding of human preferences in different tasks, we build a dataset of 100 tasks from academic papers, popular media portrayal of AI, and everyday life, and administer a survey based on our proposed framework. We find little preference for full AI control and a strong preference for machine-in-the-loop designs, in which humans play the leading role. Among the four factors, trust is the most correlated with human preferences of optimal human-machine delegation. This framework represents a first step towards characterizing human preferences of AI automation across tasks. We hope this work encourages future efforts towards understanding such individual attitudes; our goal is to inform the public and the AI research community rather than dictating any direction in technology development. |
| Tasks | |
| Published | 2019-02-08 |
| URL | https://arxiv.org/abs/1902.03245v2 |
| https://arxiv.org/pdf/1902.03245v2.pdf | |
| PWC | https://paperswithcode.com/paper/ask-not-what-ai-can-do-but-what-ai-should-do |
| Repo | |
| Framework | |
XSP: Across-Stack Profiling and Analysis of Machine Learning Models on GPUs
| Title | XSP: Across-Stack Profiling and Analysis of Machine Learning Models on GPUs |
| Authors | Cheng Li, Abdul Dakkak, Jinjun Xiong, Wei Wei, Lingjie Xu, Wen-mei Hwu |
| Abstract | There has been a rapid proliferation of machine learning/deep learning (ML) models and wide adoption of them in many application domains. This has made profiling and characterization of ML model performance an increasingly pressing task for both hardware designers and system providers, as they would like to offer the best possible system to serve ML models with the target latency, throughput, cost, and energy requirements while maximizing resource utilization. Such an endeavor is challenging as the characteristics of an ML model depend on the interplay between the model, framework, system libraries, and the hardware (or the HW/SW stack). Existing profiling tools are disjoint, however, and only focus on profiling within a particular level of the stack, which limits the thoroughness and usefulness of the profiling results. This paper proposes XSP — an across-stack profiling design that gives a holistic and hierarchical view of ML model execution. XSP leverages distributed tracing to aggregate and correlate profile data from different sources. XSP introduces a leveled and iterative measurement approach that accurately captures the latencies at all levels of the HW/SW stack in spite of the profiling overhead. We couple the profiling design with an automated analysis pipeline to systematically analyze 65 state-of-the-art ML models. We demonstrate that XSP provides insights which would be difficult to discern otherwise. |
| Tasks | |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.06869v2 |
| https://arxiv.org/pdf/1908.06869v2.pdf | |
| PWC | https://paperswithcode.com/paper/across-stack-profiling-and-characterization |
| Repo | |
| Framework | |
Vehicle routing by learning from historical solutions
| Title | Vehicle routing by learning from historical solutions |
| Authors | Rocsildes Canoy, Tias Guns |
| Abstract | The goal of this paper is to investigate a decision support system for vehicle routing, where the routing engine learns from the subjective decisions that human planners have made in the past, rather than optimizing a distance-based objective criterion. This is an alternative to the practice of formulating a custom VRP for every company with its own routing requirements. Instead, we assume the presence of past vehicle routing solutions over similar sets of customers, and learn to make similar choices. The approach is based on the concept of learning a first-order Markov model, which corresponds to a probabilistic transition matrix, rather than a deterministic distance matrix. This nevertheless allows us to use existing arc routing VRP software in creating the actual route plans. For the learning, we explore different schemes to construct the probabilistic transition matrix. Our results on a use-case with a small transportation company show that our method is able to generate results that are close to the manually created solutions, without needing to characterize all constraints and sub-objectives explicitly. Even in the case of changes in the client sets, our method is able to find solutions that are closer to the actual route plans than when using distances, and hence, solutions that would require fewer manual changes to transform into the actual route plan. |
| Tasks | |
| Published | 2019-09-17 |
| URL | https://arxiv.org/abs/1909.07893v1 |
| https://arxiv.org/pdf/1909.07893v1.pdf | |
| PWC | https://paperswithcode.com/paper/vehicle-routing-by-learning-from-historical |
| Repo | |
| Framework | |
Mastering emergent language: learning to guide in simulated navigation
| Title | Mastering emergent language: learning to guide in simulated navigation |
| Authors | Mathijs Mul, Diane Bouchacourt, Elia Bruni |
| Abstract | To cooperate with humans effectively, virtual agents need to be able to understand and execute language instructions. A typical setup to achieve this is with a scripted teacher which guides a virtual agent using language instructions. However, such setup has clear limitations in scalability and, more importantly, it is not interactive. Here, we introduce an autonomous agent that uses discrete communication to interactively guide other agents to navigate and act on a simulated environment. The developed communication protocol is trainable, emergent and requires no additional supervision. The emergent language speeds up learning of new agents, it generalizes across incrementally more difficult tasks and, contrary to most other emergent languages, it is highly interpretable. We demonstrate how the emitted messages correlate with particular actions and observations, and how new agents become less dependent on this guidance as training progresses. By exploiting the correlations identified in our analysis, we manage to successfully address the agents in their own language. |
| Tasks | |
| Published | 2019-08-14 |
| URL | https://arxiv.org/abs/1908.05135v1 |
| https://arxiv.org/pdf/1908.05135v1.pdf | |
| PWC | https://paperswithcode.com/paper/mastering-emergent-language-learning-to-guide |
| Repo | |
| Framework | |
