Match!
arXiv: Learning
Papers
19689
Papers 19490
1 page of 1,949 pages (19.5k results)
Newest
#1Diego Álvarez-Estévez (University of A Coruña)H-Index: 8
In this work we examine some of the problems associated with the development of machine learning models with the objective to achieve robust generalization capabilities on common-task multiple-database scenarios. Referred to as the "database variability problem", we focus on a specific medical domain (sleep staging in sleep medicine) to show the non-triviality of translating the estimated model's local generalization capabilities into independent external databases. We analyze some of the scalab...
#1Wenjin Wang (ZJU: Zhejiang University)
#2Yunqing Hu (ZJU: Zhejiang University)
Last. Yin Zhang (ZJU: Zhejiang University)
view all 3 authors...
Lifelong learning remains an open problem. One of its main difficulties is catastrophic forgetting. Many dynamic expansion approaches have been proposed to address this problem, but they all use homogeneous models of predefined structure for all tasks. The common original model and expansion structures ignore the requirement of different model structures on different tasks, which leads to a less compact model for multiple tasks and causes the model size to increase rapidly as the number of tasks...
#1Maria-Florina Balcan (CMU: Carnegie Mellon University)H-Index: 33
#2Travis Dick (CMU: Carnegie Mellon University)H-Index: 7
Last. Dravyansh Sharma (CMU: Carnegie Mellon University)
view all 3 authors...
Optimization in the presence of sharp (non-Lipschitz), unpredictable (w.r.t.\ time and amount) changes is a challenging and largely unexplored problem of great significance. We consider the class of piecewise Lipschitz functions, which is the most general setting considered in the literature for the problem, and arises naturally in various combinatorial algorithm selection problems where utility functions can have sharp discontinuities. The usual performance metric of `static' regret minimizes t...
#1Xin Sun (NTU: Nanyang Technological University)
#2Zhenning Yang (NTU: Nanyang Technological University)
Last. Keck Voon Ling (NTU: Nanyang Technological University)H-Index: 20
view all 5 authors...
Deep neural networks have achieved state-of-the-art performance in a wide range of recognition/classification tasks. However, when applying deep learning to real-world applications, there are still multiple challenges. A typical challenge is that unknown samples may be fed into the system during the testing phase and traditional deep neural networks will wrongly recognize the unknown sample as one of the known classes. Open set recognition is a potential solution to overcome this problem, where ...
#1Hrushikesh LoyaH-Index: 1
#2Pranav PoduvalH-Index: 1
Last. Amit SethiH-Index: 13
view all 5 authors...
Survival models are used in various fields, such as the development of cancer treatment protocols. Although many statistical and machine learning models have been proposed to achieve accurate survival predictions, little attention has been paid to obtain well-calibrated uncertainty estimates associated with each prediction. The currently popular models are opaque and untrustworthy in that they often express high confidence even on those test cases that are not similar to the training samples, an...
#1Brandon CarterH-Index: 2
#2Siddhartha JainH-Index: 7
Last. David K. GiffordH-Index: 59
view all 4 authors...
Image classifiers are typically scored on their test set accuracy, but high accuracy can mask a subtle type of model failure. We find that high scoring convolutional neural networks (CNN) exhibit troubling pathologies that allow them to display high accuracy even in the absence of semantically salient features. When a model provides a high-confidence decision without salient supporting input features we say that the classifier has overinterpreted its input, finding too much class-evidence in pat...
Federated learning enables machine learning models to learn from private decentralized data without compromising privacy. The standard formulation of federated learning produces one shared model for all clients. Statistical heterogeneity due to non-IID distribution of data across devices often leads to scenarios where, for some clients, the local models trained solely on their private data perform better than the global shared model thus taking away their incentive to participate in the process....
Convolutional Neural Networks (CNNs) have shown remarkable performance in general object recognition tasks. In this paper, we propose a new model called EnsNet which is composed of one base CNN and multiple Fully Connected SubNetworks (FCSNs). In this model, the set of feature-maps generated by the last convolutional layer in the base CNN is divided along channels into disjoint subsets, and these subsets are assigned to the FCSNs. Each of the FCSNs is trained independent of others so that it can...
#1Maurice WeberH-Index: 1
#2Xiaojun XuH-Index: 1
Last. Bo LiH-Index: 24
view all 5 authors...
Recent studies have shown that deep neural networks (DNNs) are vulnerable to various attacks, including evasion attacks and poisoning attacks. On the defense side, there have been intensive interests in provable robustness against evasion attacks. In this paper, we focus on improving model robustness against more diverse threat models. Specifically, we provide the first unified framework using smoothing functional to certify the model robustness against general adversarial attacks. In particular...
#1Ali BalaliH-Index: 3
#2Masoud AsadpourH-Index: 15
Last. Adam JatowtH-Index: 19
view all 4 authors...
Event extraction (EE) is one of the core information extraction tasks, whose purpose is to automatically identify and extract information about incidents and their actors from texts. This may be beneficial to several domains such as knowledge bases, question answering, information retrieval and summarization tasks, to name a few. The problem of extracting event information from texts is longstanding and usually relies on elaborately designed lexical and syntactic features, which, however, take a...
12345678910
Top fields of study
Machine learning
Mathematical optimization
Mathematics
Artificial neural network
Reinforcement learning