In two typical cross-domain semantic segmentation tasks, i. e., GTA5 to Cityscapes and SYNTHIA to Cityscapes, our method achieves the state-of-the-art segmentation accuracy.
One of the key challenges in visual Reinforcement Learning (RL) is to learn policies that can generalize to unseen environments.
Then, we design a counterfactual verification module to verify the BTPK-based learning method.
The dynamic job-shop scheduling problem (DJSP) is a class of scheduling tasks that specifically consider the inherent uncertainties such as changing order requirements and possible machine breakdown in realistic smart manufacturing settings.
The integration of Reinforcement Learning (RL) and Evolutionary Algorithms (EAs) aims at simultaneously exploiting the sample efficiency as well as the diversity and robustness of the two paradigms.
In general, IL methods can be categorized into Behavioral Cloning (BC) and Inverse Reinforcement Learning (IRL).
Under the increasing need to decarbonize energy systems, there is coupled acceleration in connection of distributed and intermittent renewable resources in power grids.
Filter pruning has been widely used for neural network compression because of its enabled practical acceleration.
Based on the observations and outcomes from our analysis, we then propose SPARK, a unified DNN compression framework that can simultaneously capture model SPArsity and low-RanKness in an efficient way.
It is also the first time in this field that an algorithm design for intelligent wargaming combines multi-attribute decision making with reinforcement learning.
Researchers are increasingly focusing on intelligent games as a hot research area. The article proposes an algorithm that combines the multi-attribute management and reinforcement learning methods, and that combined their effect on wargaming, it solves the problem of the agent's low rate of winning against specific rules and its inability to quickly converge during intelligent wargame training. At the same time, this paper studied a multi-attribute decision making and reinforcement learning algorithm in a wargame simulation environment, and obtained data on red and blue conflict. Calculate the weight of each attribute based on the intuitionistic fuzzy number weight calculations.
In CDaKD, we exploit online clustering to achieve context division, and interference is further alleviated by a knowledge distillation regularization term on the output layers for learned contexts.
Notably, on CIFAR-100, with 2. 3X and 2. 4X compression ratios, our models have 1. 96% and 2. 21% higher top-1 accuracy than the original ResNet-20 and ResNet-32, respectively.
While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected.
With the development of Edge Computing and Artificial Intelligence (AI) technologies, edge devices are witnessed to generate data at unprecedented volume.
Multi-view clustering is an important yet challenging task in machine learning and data mining community.
While there is no analogous ground truth for real life biological systems, this work demonstrates the ability to construct and parameterize a considerable diversity of network models with high predictive ability.
Although various prior works have been proposed to reduce the RNN model sizes, executing RNN models in resource-restricted environments is still a very challenging problem.
In this paper, we, for the first time, perform systematic investigation on noise injection-based regularization for point cloud-domain DNNs.
Recently deep neural networks have been successfully applied in channel coding to improve the decoding performance.
In recent studies, Lots of work has been done to solve time series anomaly detection by applying Variational Auto-Encoders (VAEs).
Experiments show that the proxy can effectively curb the increase of the combined risk when minimizing the source risk and distribution discrepancy.
no code implementations • 25 Nov 2020 • Deheng Ye, Guibin Chen, Peilin Zhao, Fuhao Qiu, Bo Yuan, Wen Zhang, Sheng Chen, Mingfei Sun, Xiaoqian Li, Siqin Li, Jing Liang, Zhenjie Lian, Bei Shi, Liang Wang, Tengfei Shi, Qiang Fu, Wei Yang, Lanxiao Huang
Unlike prior attempts, we integrate the macro-strategy and the micromanagement of MOBA-game-playing into neural networks in a supervised and end-to-end manner.
no code implementations • • Deheng Ye, Guibin Chen, Wen Zhang, Sheng Chen, Bo Yuan, Bo Liu, Jia Chen, Zhao Liu, Fuhao Qiu, Hongsheng Yu, Yinyuting Yin, Bei Shi, Liang Wang, Tengfei Shi, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu
However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i. e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes.
We consider two cases of this setting, one is that the source domain only contains complementary-label data (completely complementary unsupervised domain adaptation, CC-UDA), and the other is that the source domain has plenty of complementary-label data and a small amount of true-label data (partly complementary unsupervised domain adaptation, PC-UDA).
To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA).
To illustrate the importance of prior knowledge, the result of the algorithm without prior knowledge is also investigated.
To achieve this aim, a previous study has proven an upper bound of the target-domain risk, and the open set difference, as an important term in the upper bound, is used to measure the risk on unknown target data.
Recurrent Neural Networks (RNNs) have been widely used in sequence analysis and modeling.
These idealized assumptions, however, makes the existing audio adversarial attacks mostly impossible to be launched in a timely fashion in practice (e. g., playing unnoticeable adversarial perturbations along with user's streaming input).
On the other hand, the recent structured matrix-based approach (i. e., CirCNN) is limited by the relatively complex arithmetic computation (i. e., FFT), less flexible compression ratio, and its inability to fully utilize input sparsity.
As the popularity of voice user interface (VUI) exploded in recent years, speaker recognition system has emerged as an important medium of identifying a speaker in many security-required applications and services.
In addition, CAG exhibits high transferability across different DNN classifier models in black-box attack scenario by introducing random dropout in the process of generating perturbations.
In this paper, we present AdversarialPSO, a black-box attack that uses fewer queries to create adversarial examples with high success rates.
Experimental evaluation is a major research methodology for investigating clustering algorithms and many other machine learning algorithms.
Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications.
Network representation learning (NRL) has been widely used to help analyze large-scale networks through mapping original networks into a low-dimensional vector space.
Ranked #1 on Link Prediction on IMDb
Based on the developed guideline and adaptive dropping mechanism, an innovative soft-guided adaptively-dropped (SGAD) neural network is proposed in this paper.
Recently, Deep Convolutional Neural Network (DCNN) has achieved tremendous success in many machine learning applications.
For FPGA implementations on deep convolutional neural networks (DCNNs), we achieve at least 152X and 72X improvement in performance and energy efficiency, respectively using the SWM-based framework, compared with the baseline of IBM TrueNorth processor under same accuracy constraints using the data set of MNIST, SVHN, and CIFAR-10.
Based on the universal approximation property, we further prove that SCNNs and BNNs exhibit the same energy complexity.
The previous work proposes to use a pruning based compression technique to reduce the model size and thus speedups the inference on FPGAs.
Hardware accelerations of deep learning systems have been extensively investigated in industry and academia.
no code implementations • 29 Aug 2017 • Caiwen Ding, Siyu Liao, Yanzhi Wang, Zhe Li, Ning Liu, Youwei Zhuo, Chao Wang, Xuehai Qian, Yu Bai, Geng Yuan, Xiaolong Ma, Yi-Peng Zhang, Jian Tang, Qinru Qiu, Xue Lin, Bo Yuan
As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performance while maintaining accuracy.
Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks.
Stochastic Computing (SC), which uses bit-stream to represent a number within [-1, 1] by counting the number of ones in the bit-stream, has a high potential for implementing DCNNs with high scalability and ultra-low hardware footprint.