检索结果-内蒙古大学图书馆

Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Nguyen, Thanh Xuan Luu, Tung Pham, Trung Rakhimkul, Sanzhar Yoo, Chang D. Korea Republic of

Model agnostic meta-learning (MAML) is a popular state-of-the-art meta-learning algorithm that provides good weight initialization of a model given a variety of learning tasks. The model initialized by provided weight can be fine-tuned to an unseen task despite only using a small amount of samples and within a few adaptation steps. MAML is simple and versatile but requires costly learning rate tuning and careful design of the task distribution which affects its scalability and generalization. This paper proposes a more robust MAML based on an adaptive learning scheme and a prioritization task buffer (PTB) referred to as Robust MAML (RMAML) for improving scalability of training process and alleviating the problem of distribution mismatch. RMAML uses gradient-based hyper-parameter optimization to automatically find the optimal learning rate and uses the PTB to gradually adjust training task distribution toward testing task distribution over the course of training. Experimental results on meta reinforcement learning environments demonstrate a substantial performance gain as well as being less sensitive to hyper-parameter choice and robust to distribution mismatch. © 2021, CC BY-NC-ND.

关键词： learning algorithms

CrossedWires: A dataset of syntactically equivalent but semantically disparate deep learning models

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zvyagin, Max Brettin, Thomas Ramanathan, Arvind Jha, Sumit K. Argonne National Laboratory LemontIL64309 United States Computer Science Department University of Texas at San Antonio

The training of neural networks using different deep learning frameworks may lead to drastically differing accuracy levels despite the use of the same neural network architecture and identical training hyperparameters such as learning rate and choice of optimization algorithms. Currently, our ability to build standardized deep learning models is limited by the availability of a suite of neural network and corresponding training hyperparameter benchmarks that expose differences between existing deep learning frameworks. In this paper, we present a living dataset of models and hyperparameters, called CrossedWires, that exposes semantic differences between two popular deep learning frameworks: PyTorch and Tensorflow. The CrossedWires dataset currently consists of models trained on CIFAR10 images using three different computer vision architectures: VGG16, ResNet50 and DenseNet121 across a large hyperparameter space. Using hyperparameter optimization, each of the three models was trained on 400 sets of hyperparameters suggested by the HyperSpace search algorithm. The CrossedWires dataset includes PyTorch and Tensforflow models with test accuracies as different as 0.681 on syntactically equivalent models and identical hyperparameter choices. The 340 GB dataset and benchmarks presented here include the performance statistics, training curves, and model weights for all 1200 hyperparameter choices, resulting in 2400 total models. The CrossedWires dataset provides an opportunity to study semantic differences between syntactically equivalent models across popular deep learning frameworks. Further, the insights obtained from this study can enable the development of algorithms and tools that improve reliability and reproducibility of deep learning frameworks. The dataset is freely available at https://***/maxzvyagin/crossedwires through a Python API and direct download link. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

Regret analysis in deterministic reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Tranos, Damianos Proutiere, Alexandre Stockholm Sweden

We consider Markov Decision Processes (MDPs) with deterministic transitions and study the problem of regret minimization, which is central to the analysis and design of optimal learning algorithms. We present logarithmic problem-specific regret lower bounds that explicitly depend on the system parameter (in contrast to previous minimax approaches) and thus, truly quantify the fundamental limit of performance achievable by any learning algorithm. Deterministic MDPs can be interpreted as graphs and analyzed in terms of their cycles, a fact which we leverage in order to identify a class of deterministic MDPs whose regret lower bound can be determined numerically. We further exemplify this result on a deterministic line search problem, and a deterministic MDP with state-dependent rewards, whose regret lower bounds we can state explicitly. These bounds share similarities with the known problem-specific bound of the multi-armed bandit problem and suggest that navigation on a deterministic MDP need not have an effect on the performance of a learning algorithm. © 2021, CC BY.

关键词： learning algorithms

N-Omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Yang Dong, Yiting Zhao, Dongcheng Zeng, Yi Brain-inspired Cognitive Intelligence Lab Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China School of Future Technology University of Chinese Academy of Sciences Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China

Few-shot learning (learning with a few samples) is one of the most important cognitive abilities of the human brain. However, the current artificial intelligence systems meet difficulties in achieving this ability. Similar challenges also exist for biologically plausible spiking neural networks (SNNs). Datasets for traditional few-shot learning domains provide few amounts of temporal information. and the absence of neuromorphic datasets has hindered the development of few-shot learning for SNNs. Here, to the best of our knowledge, we provide the first neuromorphic dataset for few-shot learning using SNNs: N-Omniglot, based on the Dynamic Vision Sensor. It contains 1,623 categories of handwritten characters, with only 20 samples per class. N-Omniglot eliminates the need for a neuromorphic dataset for SNNs with high spareness and tremendous temporal coherence. Additionally, the dataset provides a powerful challenge and a suitable benchmark for developing SNNs algorithms in the few-shot learning domain due to the chronological information of strokes. We also provide the improved nearest neighbor, convolutional network, SiameseNet, and meta-learning algorithm in the spiking version for verification. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

SAGCI-System: Towards Sample-Efficient, Generalizable, Compositional, and Incremental Robot learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lv, Jun Yu, Qiaojun Shao, Lin Liu, Wenhai Xu, Wenqiang Lu, Cewu Department of Computer Science Shanghai Jiao Tong University China Artificial Intelligence Lab Stanford University United States School of Mechanical Engineering Shanghai Jiao Tong University China

Building general-purpose robots to perform a diverse range of tasks in a large variety of environments in the physical world at the human level is extremely challenging. According to [1], it requires the robot learning to be sample-efficient, generalizable, compositional, and incremental. In this work, we introduce a systematic learning framework called SAGCI-system towards achieving these above four requirements. Our system first takes the raw point clouds gathered by the camera mounted on the robot’s wrist as the inputs and produces initial modeling of the surrounding environment represented as a file of Unified Robot Description Format (URDF). Our system adopts a learning-augmented differentiable simulation that loads the URDF. The robot then utilizes the interactive perception to interact with the environment to online verify and modify the URDF. Leveraging the differentiable simulation, we propose a model-based learning algorithm combining object-centric and robot-centric stages to efficiently produce policies to accomplish manipulation tasks. We apply our system to perform articulated object manipulation tasks, both in the simulation and the real world. Extensive experiments demonstrate the effectiveness of our proposed learning framework. Supplemental materials and videos are available on our project webpage https://***/view/egci. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

A novel heuristic algorithm: adaptive and various learning-based algorithm

学校读者我要写书评

暂无评论

arXiv 2025年

作者： He, Sheng-Xue Business School University of Shanghai for Science and Technology Shanghai200093 China

A novel population-based heuristic algorithm called the adaptive and various learning-based algorithm (AVLA) is proposed for solving general optimization problems in this paper. The main idea of AVLA is inspired by the learning behaviors of individuals in a group, e.g. a school class. The algorithm formulates the following learning behaviors: a. Elite members will learn from each other;b. A common member will learn from some elite member and other common members;c. Members with unsatisfied performance will reflect their behavior after performance estimation;d. The whole group will reflect their behavior and try to improve if the performance of the group as a whole has not been improved for a long time. AVLA adopts the success-history based parameter adaptation to lighten the burden of parameter adjustment. To verify the efficiency of the AVLA, we apply it and its no-adaptation version with other eight well-known heuristics to 100 benchmark problems. The comparison clearly shows that AVLA performs as well as SHADE and the non-adaption version of AVLA outperforms others except AVLA and *** Codes 90 © 2025, CC BY-NC-ND.

关键词： learning algorithms

learning bias-invariant representation by cross-sample mutual information minimization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhu, Wei Zheng, Haitian Liao, Haofu Li, Weijian Luo, Jiebo University of Rochester Amazon Web Services

Deep learning algorithms mine knowledge from the training data and thus would likely inherit the dataset's bias information. As a result, the obtained model would generalize poorly and even mislead the decision process in real-life applications. We propose to remove the bias information misused by the target task with a cross-sample adversarial debiasing (CSAD) method. CSAD explicitly extracts target and bias features disentangled from the latent representation generated by a feature extractor and then learns to discover and remove the correlation between the target and bias features. The correlation measurement plays a critical role in adversarial debiasing and is conducted by a cross-sample neural mutual information estimator. Moreover, we propose joint content and local structural representation learning to boost mutual information estimation for better performance. We conduct thorough experiments on publicly available datasets to validate the advantages of the proposed method over state-of-the-art approaches. © 2021, CC BY.

关键词： learning algorithms

AdaptCL: Efficient collaborative learning with dynamic and adaptive pruning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Guangmeng Xu, Ke Li, Qi Liu, Yang Zhao, Yi Department of Computer Science and Technology Tsinghua University Beijing China

In multi-party collaborative learning, the parameter server sends a global model to each data holder for local training and then aggregates committed models globally to achieve privacy protection. However, both the dragger issue of synchronous collaborative learning and the staleness issue of asynchronous collaborative learning make collaborative learning inefficient in real-world heterogeneous environments. We propose a novel and efficient collaborative learning framework named AdaptCL, which generates an adaptive sub-model dynamically from the global base model for each data holder, without any prior information about worker capability. All workers (data holders) achieve approximately identical update time as the fastest worker by equipping them with capability-adapted pruned models. Thus the training process can be dramatically accelerated. Besides, we tailor the efficient pruned rate learning algorithm and pruning approach for AdaptCL. Meanwhile, AdaptCL provides a mechanism for handling the trade-off between accuracy and time overhead and can be combined with other techniques to accelerate training further. Empirical results show that AdaptCL introduces little computing and communication overhead. AdaptCL achieves time savings of more than 41% on average and improves accuracy in a low heterogeneous environment. In a highly heterogeneous environment, AdaptCL achieves a training speedup of 6.2x with a slight loss of accuracy. Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms

A contrastive rule for meta-learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zucchet, Nicolas von Oswald, Johannes Schug, Simon Zhao, Dominic Sacramento, João Department of Computer Science ETH Zürich Switzerland Institute of Neuroinformatics University of Zürich ETH Zürich Switzerland

Humans and other animals are capable of improving their learning performance as they solve related tasks from a given problem domain, to the point of being able to learn from extremely limited data. While synaptic plasticity is generically thought to underlie learning in the brain, the precise neural and synaptic mechanisms by which learning processes improve through experience are not well understood. Here, we present a general-purpose, biologically-plausible meta-learning rule which estimates gradients with respect to the parameters of an underlying learning algorithm by simply running it twice. Our rule may be understood as a generalization of contrastive Hebbian learning to meta-learning and notably, it neither requires computing second derivatives nor going backwards in time, two characteristic features of previous gradient-based methods that are hard to conceive in physical neural circuits. We demonstrate the generality of our rule by applying it to two distinct models: a complex synapse with internal states which consolidate task-shared information, and a dual-system architecture in which a primary network is rapidly modulated by another one to learn the specifics of each task. For both models, our meta-learning rule matches or outperforms reference algorithms on a wide range of benchmark problems, while only using information presumed to be locally available at neurons and synapses. We corroborate these findings with a theoretical analysis of the gradient estimation error incurred by our rule.1 Copyright © 2021, The Authors. All rights reserved.

关键词： learning algorithms