检索结果-内蒙古大学图书馆

Spatial assembly: Generative architecture with reinforcement learning, self play and tree search

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Tigas, Panagiotis Hosmer, Tyson University of Oxford United Kingdom Bartlett School of Architecture UCL United Kingdom

With this work, we investigate the use of Reinforcement learning (RL) for generation of spatial assemblies, by combining ideas from Procedural Generation algorithms (Wave Function Collapse algorithm (WFC) [8]) and RL for Game Solving. WFC is a Generative Design algorithm, inspired by Constraint Solving [3]. In WFC, one defines a set of tiles/blocks and constraints and the algorithm generates an assembly that satisfies these constraints. Casting the problem of generation of spatial assemblies as a Markov Decision Process whose states transitions are defined by WFC, we propose an algorithm that uses Reinforcement learning and Self-Play to learn a policy that generates assemblies which maximize objectives set by the designer. Finally, we demonstrate the use of our Spatial Assembly algorithm in Architecture Design. © 2021, CC BY.

关键词： learning algorithms

Unifying distillation with personalization in federated learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Divi, Siddharth Farrukh, Habiba Celik, Z. Berkay Purdue University West Lafayette United States

Federated learning (FL) is a decentralized privacy-preserving learning technique in which clients learn a joint collaborative model through a central aggregator without sharing their data. In this setting, all clients learn a single common predictor (FedAvg), which does not generalize well on each client's local data due to the statistical data heterogeneity among clients. In this paper, we address this problem with PersFL, a discrete two-stage personalized learning algorithm. In the first stage, PersFL finds the optimal teacher model of each client during the FL training phase. In the second stage, PersFL distills the useful knowledge from optimal teachers into each user's local model. The teacher model provides each client with some rich, high-level representation that a client can easily adapt to its local model, which overcomes the statistical heterogeneity present at different clients. We evaluate PersFL on CIFAR-10 and MNIST datasets using three data-splitting strategies to control the diversity between clients' data distributions. We empirically show that PersFL outperforms FedAvg and three state-of-the-art personalization methods, pFedMe, Per-FedAvg and FedPer on majority data-splits with minimal communication cost. Further, we study the performance of PersFL on different distillation objectives, how this performance is affected by the equitable notion of fairness among clients, and the number of required communication rounds. PersFL code is available at https://***/hdh5zhxs for public use and validation. © 2021, CC BY.

关键词： learning algorithms

Meta-learning amidst heterogeneity and ambiguity

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Go, Kyeongryeol Yun, Seyoung Graduate School of AI KAIST Daejeon Korea Republic of

Meta-learning aims to learn a model that can handle multiple tasks generated from an unknown but shared distribution. However, typical meta-learning algorithms have assumed the tasks to be similar such that a single meta-learner is sufficient to aggregate the variations in all aspects. In addition, there has been less consideration on uncertainty when limited information is given as context. In this paper, we devise a novel meta-learning framework, called Meta-learning Amidst Heterogeneity and Ambiguity (MAHA), that outperforms previous works in terms of prediction based on its ability on task identification. By extensively conducting several experiments in regression and classification, we demonstrate the validity of our model, which turns out to be robust to both task heterogeneity and ambiguity. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

An instance-dependent simulation framework for learning with label noise

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gu, Keren Masotto, Xander Bachani, Vandana Lakshminarayanan, Balaji Nikodem, Jack Yin, Dong DeepMind Google Research Brain Team

We propose a simulation framework for generating instance-dependent noisy labels via a pseudo-labeling paradigm. We show that the distribution of the synthetic noisy labels generated with our framework is closer to human labels compared to independent and class-conditional random flipping. Equipped with controllable label noise, we study the negative impact of noisy labels across a few practical settings to understand when label noise is more problematic. We also benchmark several existing algorithms for learning with noisy labels and compare their behavior on our synthetic datasets and on the datasets with independent random label noise. Additionally, with the availability of annotator information from our simulation framework, we propose a new technique, Label Quality Model (LQM), that leverages annotator features to predict and correct against noisy labels. We show that by adding LQM as a label correction step before applying existing noisy label techniques, we can further improve the models' performance. The synthetic datasets that we generated in this work are released at https://***/deepmind/deepmind-research/ tree/master/noisy_label. © 2021, CC BY.

关键词： learning algorithms

Deep learning for Instance Retrieval: A Survey

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Wei Liu, Yu Wang, Weiping Bakker, Erwin M. Georgiou, Theodoros Fieguth, Paul Liu, Li Lew, Michael S. Academy of Advanced Technology Research of Hunan Changsha China DUTRU International School of Information Science and Engineering Dalian University of Technology China Leiden Institute of Advanced Computer Science Leiden University Netherlands The Department of Systems Design Engineering University of Waterloo Canada Center for Machine Vision and Signal Analysis University of Oulu Finland

In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics. This abundance of content creation and sharing has introduced new challenges, particularly that of searching databases for similar content - Content Based Image Retrieval (CBIR) - a long-established research area in which improved efficiency and accuracy are needed for real-time retrieval. Artificial intelligence has made progress in CBIR and has significantly facilitated the process of instance search. In this survey we review recent instance retrieval works that are developed based on deep learning algorithms and techniques, with the survey organized by deep feature extraction, feature embedding and aggregation methods, and network fine-tuning strategies. Our survey considers a wide variety of recent methods, whereby we identify milestone work, reveal connections among various methods and present the commonly used benchmarks, evaluation results, common challenges, and propose promising future directions. © 2021, CC BY-NC-SA.

关键词： learning algorithms

Meta-learning with an adaptive task scheduler

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yao, Huaxiu Wang, Yu Wei, Ying Zhao, Peilin Mahdavi, Mehrdad Lian, Defu Finn, Chelsea Stanford University University of Science and Technology Tencent AI Lab Pennsylvania State University City University of Hong Kong

To benefit the learning of a new task, meta-learning has been proposed to transfer a well-generalized meta-model learned from various meta-training tasks. Existing meta-learning algorithms randomly sample meta-training tasks with a uniform probability, under the assumption that tasks are of equal importance. However, it is likely that tasks are detrimental with noise or imbalanced given a limited number of meta-training tasks. To prevent the meta-model from being corrupted by such detrimental tasks or dominated by tasks in the majority, in this paper, we propose an adaptive task scheduler (ATS) for the meta-training process. In ATS, for the first time, we design a neural scheduler to decide which meta-training tasks to use next by predicting the probability being sampled for each candidate task, and train the scheduler to optimize the generalization capacity of the meta-model to unseen tasks. We identify two meta-model-related factors as the input of the neural scheduler, which characterize the difficulty of a candidate task to the meta-model. Theoretically, we show that a scheduler taking the two factors into account improves the meta-training loss and also the optimization landscape. Under the setting of meta-learning with noise and limited budgets, ATS improves the performance on both miniImageNet and a real-world drug discovery benchmark by up to 13% and 18%, respectively, compared to state-of-the-art task schedulers. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

Human-robot collaboration and machine learning: a systematic review of recent research

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Semeraro, Francesco Griffiths, Alexander Cangelosi, Angelo Cognitive Robotics Laboratory The University of Manchester Manchester United Kingdom Ltd. Warton Aerodrome Lancashire United Kingdom

Technological progress increasingly envisions the use of robots interacting with people in everyday life. Human-robot collaboration (HRC) is the approach that explores the interaction between a human and a robot, during the completion of a common objective, at the cognitive and physical level. In HRC works, a cognitive model is typically built, which collects inputs from the environment and from the user, elaborates and translates these into information that can be used by the robot itself. Machine learning is a recent approach to build the cognitive model and behavioural block, with high potential in HRC. Consequently, this paper proposes a thorough literature review of the use of machine learning techniques in the context of human-robot collaboration. 45 key papers were selected and analysed, and a clustering of works based on the type of collaborative tasks, evaluation metrics and cognitive variables modelled is proposed. Then, a deep analysis on different families of machine learning algorithms and their properties, along with the sensing modalities used, is carried out. Among the observations, it is outlined the importance of the machine learning algorithms to incorporate time dependencies. The salient features of these works are then cross-analysed to show trends in HRC and give guidelines for future works, comparing them with other aspects of HRC not appeared in the review. © 2021, CC BY.

关键词： learning algorithms

AutoDrop: Training deep learning models with automatic learning rate drop

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Teng, Yunfei Wang, Jing Choromanska, Anna

Modern deep learning (DL) architectures are trained using variants of the SGD algorithm that is run with a manually defined learning rate schedule, i.e., the learning rate is dropped at the pre-defined epochs, typically when the training loss is expected to saturate. In this paper we develop an algorithm that realizes the learning rate drop automatically. The proposed method, that we refer to as AutoDrop, is motivated by the observation that the angular velocity of the model parameters, i.e., the velocity of the changes of the convergence direction, for a fixed learning rate initially increases rapidly and then progresses towards soft saturation. At saturation the optimizer slows down thus the angular velocity saturation is a good indicator for dropping the learning rate. After the drop, the angular velocity "resets" and follows the previously described pattern - it increases again until saturation. We show that our method improves over SOTA training approaches: it accelerates the training of DL models and leads to a better generalization. We also show that our method does not require any extra hyperparameter tuning. AutoDrop is furthermore extremely simple to implement and computationally cheap. Finally, we develop a theoretical framework for analyzing our algorithm and provide convergence guarantees. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

Systematic evaluation of causal discovery in visual model based reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ke, Nan Rosemary Didolkar, Aniket Mittal, Sarthak Goyal, Anirudh Lajoie, Guillaume Bauer, Stefan Rezende, Danilo Bengio, Yoshua Mozer, Michael Pal, Christopher Mila Polytechnique Montréal Canada Deepmind Mila Polytechnique Montréal Canada Element AI Google AI Max Planck Institute for Intelligent Systems Germany CIFAR

Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the premise that the causal variables themselves are observed. However, for AI agents such as robots trying to make sense of their environment, the only observables are low-level variables like pixels in images. To generalize well, an agent must induce high-level variables, particularly those which are causal or are affected by causal variables. A central goal for AI and causality is thus the joint discovery of abstract representations and causal structure. However, we note that existing environments for studying causal induction are poorly suited for this objective because they have complicated task-specific causal graphs which are impossible to manipulate parametrically (e.g., number of nodes, sparsity, causal chain length, etc.). In this work, our goal is to facilitate research in learning representations of high-level variables as well as causal structures among them. In order to systematically probe the ability of methods to identify these variables and structures, we design a suite of benchmarking RL environments. We evaluate various representation learning algorithms from the literature and find that explicitly incorporating structure and modularity in models can help causal induction in model-based reinforcement learning. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms