Paper Group ANR 1417
Impact of Inference Accelerators on hardware selection. Learning from Learning Machines: Optimisation, Rules, and Social Norms. Variational Metric Scaling for Metric-Based Meta-Learning. Leveraging Semi-Supervised Learning for Fairness using Neural Networks. Reliable Smart Road Signs. Reconnaissance and Planning algorithm for constrained MDP. An En …
Impact of Inference Accelerators on hardware selection
| Title | Impact of Inference Accelerators on hardware selection |
| Authors | Dibyajyoti Pati, Caroline Favart, Purujit Bahl, Vivek Soni, Yun-chan Tsai, Michael Potter, Jiahui Guan, Xiaomeng Dong, V. Ratna Saripalli |
| Abstract | As opportunities for AI-assisted healthcare grow steadily, model deployment faces challenges due to the specific characteristics of the industry. The configuration choice for a production device can impact model performance while influencing operational costs. Moreover, in healthcare some situations might require fast, but not real time, inference. We study different configurations and conduct a cost-performance analysis to determine the optimized hardware for the deployment of a model subject to healthcare domain constraints. We observe that a naive performance comparison may not lead to an optimal configuration selection. In fact, given realistic domain constraints, CPU execution might be preferable to GPU accelerators. Hence, defining beforehand precise expectations for model deployment is crucial. |
| Tasks | |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.03060v1 |
| https://arxiv.org/pdf/1910.03060v1.pdf | |
| PWC | https://paperswithcode.com/paper/impact-of-inference-accelerators-on-hardware |
| Repo | |
| Framework | |
Learning from Learning Machines: Optimisation, Rules, and Social Norms
| Title | Learning from Learning Machines: Optimisation, Rules, and Social Norms |
| Authors | Travis LaCroix, Yoshua Bengio |
| Abstract | There is an analogy between machine learning systems and economic entities in that they are both adaptive, and their behaviour is specified in a more-or-less explicit way. It appears that the area of AI that is most analogous to the behaviour of economic entities is that of morally good decision-making, but it is an open question as to how precisely moral behaviour can be achieved in an AI system. This paper explores the analogy between these two complex systems, and we suggest that a clearer understanding of this apparent analogy may help us forward in both the socio-economic domain and the AI domain: known results in economics may help inform feasible solutions in AI safety, but also known results in AI may inform economic policy. If this claim is correct, then the recent successes of deep learning for AI suggest that more implicit specifications work better than explicit ones for solving such problems. |
| Tasks | Decision Making |
| Published | 2019-12-29 |
| URL | https://arxiv.org/abs/2001.00006v1 |
| https://arxiv.org/pdf/2001.00006v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-learning-machines-optimisation |
| Repo | |
| Framework | |
Variational Metric Scaling for Metric-Based Meta-Learning
| Title | Variational Metric Scaling for Metric-Based Meta-Learning |
| Authors | Jiaxin Chen, Li-Ming Zhan, Xiao-Ming Wu, Fu-lai Chung |
| Abstract | Metric-based meta-learning has attracted a lot of attention due to its effectiveness and efficiency in few-shot learning. Recent studies show that metric scaling plays a crucial role in the performance of metric-based meta-learning algorithms. However, there still lacks a principled method for learning the metric scaling parameter automatically. In this paper, we recast metric-based meta-learning from a Bayesian perspective and develop a variational metric scaling framework for learning a proper metric scaling parameter. Firstly, we propose a stochastic variational method to learn a single global scaling parameter. To better fit the embedding space to a given data distribution, we extend our method to learn a dimensional scaling vector to transform the embedding space. Furthermore, to learn task-specific embeddings, we generate task-dependent dimensional scaling vectors with amortized variational inference. Our method is end-to-end without any pre-training and can be used as a simple plug-and-play module for existing metric-based meta-algorithms. Experiments on mini-ImageNet show that our methods can be used to consistently improve the performance of existing metric-based meta-algorithms including prototypical networks and TADAM. |
| Tasks | Few-Shot Learning, Meta-Learning |
| Published | 2019-12-26 |
| URL | https://arxiv.org/abs/1912.11809v1 |
| https://arxiv.org/pdf/1912.11809v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-metric-scaling-for-metric-based |
| Repo | |
| Framework | |
Leveraging Semi-Supervised Learning for Fairness using Neural Networks
| Title | Leveraging Semi-Supervised Learning for Fairness using Neural Networks |
| Authors | Vahid Noroozi, Sara Bahaadini, Samira Sheikhi, Nooshin Mojab, Philip S. Yu |
| Abstract | There has been a growing concern about the fairness of decision-making systems based on machine learning. The shortage of labeled data has been always a challenging problem facing machine learning based systems. In such scenarios, semi-supervised learning has shown to be an effective way of exploiting unlabeled data to improve upon the performance of model. Notably, unlabeled data do not contain label information which itself can be a significant source of bias in training machine learning systems. This inspired us to tackle the challenge of fairness by formulating the problem in a semi-supervised framework. In this paper, we propose a semi-supervised algorithm using neural networks benefiting from unlabeled data to not just improve the performance but also improve the fairness of the decision-making process. The proposed model, called SSFair, exploits the information in the unlabeled data to mitigate the bias in the training data. |
| Tasks | Decision Making |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/1912.13230v1 |
| https://arxiv.org/pdf/1912.13230v1.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-semi-supervised-learning-for |
| Repo | |
| Framework | |
Reliable Smart Road Signs
| Title | Reliable Smart Road Signs |
| Authors | Muhammed O. Sayin, Chung-Wei Lin, Eunsuk Kang, Shinichi Shiraishi, Tamer Basar |
| Abstract | In this paper, we propose a game theoretical adversarial intervention detection mechanism for reliable smart road signs. A future trend in intelligent transportation systems is ``smart road signs” that incorporate smart codes (e.g., visible at infrared) on their surface to provide more detailed information to smart vehicles. Such smart codes make road sign classification problem aligned with communication settings more than conventional classification. This enables us to integrate well-established results in communication theory, e.g., error-correction methods, into road sign classification problem. Recently, vision-based road sign classification algorithms have been shown to be vulnerable against (even) small scale adversarial interventions that are imperceptible for humans. On the other hand, smart codes constructed via error-correction methods can lead to robustness against small scale intelligent or random perturbations on them. In the recognition of smart road signs, however, humans are out of the loop since they cannot see or interpret them. Therefore, there is no equivalent concept of imperceptible perturbations in order to achieve a comparable performance with humans. Robustness against small scale perturbations would not be sufficient since the attacker can attack more aggressively without such a constraint. Under a game theoretical solution concept, we seek to ensure certain measure of guarantees against even the worst case (intelligent) attackers that can perturb the signal even at large scale. We provide a randomized detection strategy based on the distance between the decoder output and the received input, i.e., error rate. Finally, we examine the performance of the proposed scheme over various scenarios. | |
| Tasks | |
| Published | 2019-01-30 |
| URL | https://arxiv.org/abs/1901.10622v2 |
| https://arxiv.org/pdf/1901.10622v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-game-theoretical-error-correction-framework |
| Repo | |
| Framework | |
Reconnaissance and Planning algorithm for constrained MDP
| Title | Reconnaissance and Planning algorithm for constrained MDP |
| Authors | Shin-ichi Maeda, Hayato Watahiki, Shintarou Okada, Masanori Koyama |
| Abstract | Practical reinforcement learning problems are often formulated as constrained Markov decision process (CMDP) problems, in which the agent has to maximize the expected return while satisfying a set of prescribed safety constraints. In this study, we propose a novel simulator-based method to approximately solve a CMDP problem without making any compromise on the safety constraints. We achieve this by decomposing the CMDP into a pair of MDPs; reconnaissance MDP and planning MDP. The purpose of reconnaissance MDP is to evaluate the set of actions that are safe, and the purpose of planning MDP is to maximize the return while using the actions authorized by reconnaissance MDP. RMDP can define a set of safe policies for any given set of safety constraint, and this set of safe policies can be used to solve another CMDP problem with different reward. Our method is not only computationally less demanding than the previous simulator-based approaches to CMDP, but also capable of finding a competitive reward-seeking policy in a high dimensional environment, including those involving multiple moving obstacles. |
| Tasks | |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09540v1 |
| https://arxiv.org/pdf/1909.09540v1.pdf | |
| PWC | https://paperswithcode.com/paper/reconnaissance-and-planning-algorithm-for |
| Repo | |
| Framework | |
An End-to-End Deep RL Framework for Task Arrangement in Crowdsourcing Platforms
| Title | An End-to-End Deep RL Framework for Task Arrangement in Crowdsourcing Platforms |
| Authors | Caihua Shan, Nikos Mamoulis, Reynold Cheng, Guoliang Li, Xiang Li, Yuqiu Qian |
| Abstract | In this paper, we propose a Deep Reinforcement Learning (RL) framework for task arrangement, which is a critical problem for the success of crowdsourcing platforms. Previous works conduct the personalized recommendation of tasks to workers via supervised learning methods. However, the majority of them only consider the benefit of either workers or requesters independently. In addition, they cannot handle the dynamic environment and may produce sub-optimal results. To address these issues, we utilize Deep Q-Network (DQN), an RL-based method combined with a neural network to estimate the expected long-term return of recommending a task. DQN inherently considers the immediate and future reward simultaneously and can be updated in real-time to deal with evolving data and dynamic changes. Furthermore, we design two DQNs that capture the benefit of both workers and requesters and maximize the profit of the platform. To learn value functions in DQN effectively, we also propose novel state representations, carefully design the computation of Q values, and predict transition probabilities and future states. Experiments on synthetic and real datasets demonstrate the superior performance of our framework. |
| Tasks | |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01030v1 |
| https://arxiv.org/pdf/1911.01030v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-end-to-end-deep-rl-framework-for-task |
| Repo | |
| Framework | |
Rethinking Data Augmentation: Self-Supervision and Self-Distillation
| Title | Rethinking Data Augmentation: Self-Supervision and Self-Distillation |
| Authors | Hankook Lee, Sung Ju Hwang, Jinwoo Shin |
| Abstract | Data augmentation techniques, e.g., flipping or cropping, which systematically enlarge the training dataset by explicitly generating more training samples, are effective in improving the generalization performance of deep neural networks. In the supervised setting, a common practice for data augmentation is to assign the same label to all augmented samples of the same source. However, if the augmentation results in large distributional discrepancy among them (e.g., rotations), forcing their label invariance may be too difficult to solve and often hurts the performance. To tackle this challenge, we suggest a simple yet effective idea of learning the joint distribution of the original and self-supervised labels of augmented samples. The joint learning framework is easier to train, and enables an aggregated inference combining the predictions from different augmented samples for improving the performance. Further, to speed up the aggregation process, we also propose a knowledge transfer technique, self-distillation, which transfers the knowledge of augmentation into the model itself. We demonstrate the effectiveness of our data augmentation framework on various fully-supervised settings including the few-shot and imbalanced classification scenarios. |
| Tasks | Data Augmentation, Transfer Learning |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.05872v1 |
| https://arxiv.org/pdf/1910.05872v1.pdf | |
| PWC | https://paperswithcode.com/paper/rethinking-data-augmentation-self-supervision-1 |
| Repo | |
| Framework | |
Learning in Text Streams: Discovery and Disambiguation of Entity and Relation Instances
| Title | Learning in Text Streams: Discovery and Disambiguation of Entity and Relation Instances |
| Authors | Marco Maggini, Giuseppe Marra, Stefano Melacci, Andrea Zugarini |
| Abstract | We consider a scenario where an artificial agent is reading a stream of text composed of a set of narrations, and it is informed about the identity of some of the individuals that are mentioned in the text portion that is currently being read. The agent is expected to learn to follow the narrations, thus disambiguating mentions and discovering new individuals. We focus on the case in which individuals are entities and relations, and we propose an end-to-end trainable memory network that learns to discover and disambiguate them in an online manner, performing one-shot learning, and dealing with a small number of sparse supervisions. Our system builds a not-given-in-advance knowledge base, and it improves its skills while reading unsupervised text. The model deals with abrupt changes in the narration, taking into account their effects when resolving co-references. We showcase the strong disambiguation and discovery skills of our model on a corpus of Wikipedia documents and on a newly introduced dataset, that we make publicly available. |
| Tasks | One-Shot Learning |
| Published | 2019-09-06 |
| URL | https://arxiv.org/abs/1909.05367v2 |
| https://arxiv.org/pdf/1909.05367v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-in-text-streams-discovery-and |
| Repo | |
| Framework | |
Principles alone cannot guarantee ethical AI
| Title | Principles alone cannot guarantee ethical AI |
| Authors | Brent Mittelstadt |
| Abstract | AI Ethics is now a global topic of discussion in academic and policy circles. At least 84 public-private initiatives have produced statements describing high-level principles, values, and other tenets to guide the ethical development, deployment, and governance of AI. According to recent meta-analyses, AI Ethics has seemingly converged on a set of principles that closely resemble the four classic principles of medical ethics. Despite the initial credibility granted to a principled approach to AI Ethics by the connection to principles in medical ethics, there are reasons to be concerned about its future impact on AI development and governance. Significant differences exist between medicine and AI development that suggest a principled approach in the latter may not enjoy success comparable to the former. Compared to medicine, AI development lacks (1) common aims and fiduciary duties, (2) professional history and norms, (3) proven methods to translate principles into practice, and (4) robust legal and professional accountability mechanisms. These differences suggest we should not yet celebrate consensus around high-level principles that hide deep political and normative disagreement. |
| Tasks | |
| Published | 2019-06-16 |
| URL | https://arxiv.org/abs/1906.06668v2 |
| https://arxiv.org/pdf/1906.06668v2.pdf | |
| PWC | https://paperswithcode.com/paper/ai-ethics-too-principled-to-fail |
| Repo | |
| Framework | |
A comparable study: Intrinsic difficulties of practical plant diagnosis from wide-angle images
| Title | A comparable study: Intrinsic difficulties of practical plant diagnosis from wide-angle images |
| Authors | Katsumasa Suwa, Quan Huu Cap, Ryunosuke Kotani, Hiroyuki Uga, Satoshi Kagiwada, Hitoshi Iyatomi |
| Abstract | Practical automated detection and diagnosis of plant disease from wide-angle images (i.e. in-field images containing multiple leaves using a fixed-position camera) is a very important application for large-scale farm management, in view of the need to ensure global food security. However, developing automated systems for disease diagnosis is often difficult, because labeling a reliable wide-angle disease dataset from actual field images is very laborious. In addition, the potential similarities between the training and test data lead to a serious problem of model overfitting. In this paper, we investigate changes in performance when applying disease diagnosis systems to different scenarios involving wide-angle cucumber test data captured on real farms, and propose an effective diagnostic strategy. We show that leading object recognition techniques such as SSD and Faster R-CNN achieve excellent end-to-end disease diagnostic performance only for a test dataset that is collected from the same population as the training dataset (with F1-score of 81.5% - 84.1% for diagnosed cases of disease), but their performance markedly deteriorates for a completely different test dataset (with F1-score of 4.4 - 6.2%). In contrast, our proposed two-stage systems using independent leaf detection and leaf diagnosis stages attain a promising disease diagnostic performance that is more than six times higher than end-to-end systems (with F1-score of 33.4 - 38.9%) on an unseen target dataset. We also confirm the efficiency of our proposal based on visual assessment, concluding that a two-stage model is a suitable and reasonable choice for practical applications. |
| Tasks | Object Recognition |
| Published | 2019-10-25 |
| URL | https://arxiv.org/abs/1910.11506v2 |
| https://arxiv.org/pdf/1910.11506v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-comparable-study-intrinsic-difficulties-of |
| Repo | |
| Framework | |
Explicit-Blurred Memory Network for Analyzing Patient Electronic Health Records
| Title | Explicit-Blurred Memory Network for Analyzing Patient Electronic Health Records |
| Authors | Prithwish Chakraborty, Fei Wang, Jianying Hu, Daby Sow |
| Abstract | In recent years, we have witnessed an increased interest in temporal modeling of patient records from large scale Electronic Health Records (EHR). While simpler RNN models have been used for such problems, memory networks, which in other domains were found to generalize well, are underutilized. Traditional memory networks involve diffused and non-linear operations where influence of past events on outputs are not readily quantifiable. We posit that this lack of interpretability makes such networks not applicable for EHR analysis. While networks with explicit memory have been proposed recently, the discontinuities imposed by the discrete operations make such networks harder to train and require more supervision. The problem is further exacerbated in the limited data setting of EHR studies. In this paper, we propose a novel memory architecture that is more interpretable than traditional memory networks while being easier to train than explicit memory banks. Inspired by well-known models of human cognition, we propose partitioning the external memory space into (a) a primary explicit memory block to store exact replicas of recent events to support interpretations, followed by (b) a secondary blurred memory block that accumulates salient aspects of past events dropped from the explicit block as higher level abstractions and allow training with less supervision by stabilize the gradients. We apply the model for 3 learning problems on ICU records from the MIMIC III database spanning millions of data points. Our model performs comparably to the state-of the art while also, crucially, enabling ready interpretation of the results. |
| Tasks | |
| Published | 2019-11-15 |
| URL | https://arxiv.org/abs/1911.06472v1 |
| https://arxiv.org/pdf/1911.06472v1.pdf | |
| PWC | https://paperswithcode.com/paper/explicit-blurred-memory-network-for-analyzing |
| Repo | |
| Framework | |
A Lost Croatian Cybernetic Machine Translation Program
| Title | A Lost Croatian Cybernetic Machine Translation Program |
| Authors | Sandro Skansi, Leo Mršić, Ines Skelac |
| Abstract | We are exploring the historical significance of research in the field of machine translation conducted by Bulcsu Laszlo, Croatian linguist, who was a pioneer in machine translation in Yugoslavia during the 1950s. We are focused on two important seminal papers written by members of his research group from 1959 and 1962, as well as their legacy in establishing a Croatian machine translation program based around the Faculty of Humanities and Social Sciences of the University of Zagreb in the late 1950s and early 1960s. We are exploring their work in connection with the beginnings of machine translation in the USA and USSR, motivated by the Cold War and the intelligence needs of the period. We also present the approach to machine translation advocated by the Croatian group in Yugoslavia, which is different from the usual logical approaches of the period, and his advocacy of cybernetic methods, which would be adopted as a canon by the mainstream AI community only decades later. |
| Tasks | Machine Translation |
| Published | 2019-08-20 |
| URL | https://arxiv.org/abs/1908.08917v1 |
| https://arxiv.org/pdf/1908.08917v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-lost-croatian-cybernetic-machine |
| Repo | |
| Framework | |
FORECAST-CLSTM: A New Convolutional LSTM Network for Cloudage Nowcasting
| Title | FORECAST-CLSTM: A New Convolutional LSTM Network for Cloudage Nowcasting |
| Authors | Chao Tan, Xin Feng, Jianwu Long, Li Geng |
| Abstract | With the highly demand of large-scale and real-time weather service for public, a refinement of short-time cloudage prediction has become an essential part of the weather forecast productions. To provide a weather-service-compliant cloudage nowcasting, in this paper, we propose a novel hierarchical Convolutional Long-Short-Term Memory network based deep learning model, which we term as FORECAST-CLSTM, with a new Forecaster loss function to predict the future satellite cloud images. The model is designed to fuse multi-scale features in the hierarchical network structure to predict the pixel value and the morphological movement of the cloudage simultaneously. We also collect about 40K infrared satellite nephograms and create a large-scale Satellite Cloudage Map Dataset(SCMD). The proposed FORECAST-CLSTM model is shown to achieve better prediction performance compared with the state-of-the-art ConvLSTM model and the proposed Forecaster Loss Function is also demonstrated to retain the uncertainty of the real atmosphere condition better than conventional loss function. |
| Tasks | |
| Published | 2019-05-19 |
| URL | https://arxiv.org/abs/1905.07700v1 |
| https://arxiv.org/pdf/1905.07700v1.pdf | |
| PWC | https://paperswithcode.com/paper/forecast-clstm-a-new-convolutional-lstm |
| Repo | |
| Framework | |
A pedestrian path-planning model in accordance with obstacle’s danger with reinforcement learning
| Title | A pedestrian path-planning model in accordance with obstacle’s danger with reinforcement learning |
| Authors | Thanh-Trung Trinh, Dinh-Minh Vu, Masaomi Kimura |
| Abstract | Most microscopic pedestrian navigation models use the concept of “forces” applied to the pedestrian agents to replicate the navigation environment. While the approach could provide believable results in regular situations, it does not always resemble natural pedestrian navigation behaviour in many typical settings. In our research, we proposed a novel approach using reinforcement learning for simulation of pedestrian agent path planning and collision avoidance problem. The primary focus of this approach is using human perception of the environment and danger awareness of interferences. The implementation of our model has shown that the path planned by the agent shares many similarities with a human pedestrian in several aspects such as following common walking conventions and human behaviours. |
| Tasks | |
| Published | 2019-12-06 |
| URL | https://arxiv.org/abs/1912.02945v1 |
| https://arxiv.org/pdf/1912.02945v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-pedestrian-path-planning-model-in |
| Repo | |
| Framework | |
