Successful performance of machine learning approaches for object classification requires training with data sets that are good representations of actual field data. Most open source image databases, while large in siz...
详细信息
ISBN:
(纸本)9781510636040
Successful performance of machine learning approaches for object classification requires training with data sets that are good representations of actual field data. Most open source image databases, while large in size, are not representative of the type of scenes encountered by Army ground missions. The CCDC Army Research Laboratory hosts datasets, some collected recently, and some a few years ago that focus on Army scenarios and are thus an appropriate source of training data for defense applications. This paper presents examples of several of these datasets along with conditions of their availability to external research collaborators.
Manifold learning algorithms have been proven to be capable of discovering some nonlinear structures. However, it is hard for them to extend to test set directly. In this paper, a simple yet effective extension algori...
详细信息
ISBN:
(纸本)9783540723820
Manifold learning algorithms have been proven to be capable of discovering some nonlinear structures. However, it is hard for them to extend to test set directly. In this paper, a simple yet effective extension algorithm called PIE is proposed. Unlike LPP, which is linear in nature, our method is nonlinear. Besides, our method will never suffer from the singularity problem while LPP and KLPP will. Experimental results of data visualization and classification validate the effectiveness of our proposed method.
There is rapidly growing interest in using Bayesian optimization to tune model and inference hyperparameters for machine learning algorithms that take a long time to run. For example, Spearmint is a popular software p...
详细信息
There is rapidly growing interest in using Bayesian optimization to tune model and inference hyperparameters for machine learning algorithms that take a long time to run. For example, Spearmint is a popular software package for selecting the optimal number of layers and learning rate in neural networks. But given that there is uncertainty about which hyperparameters give the best predictive performance, and given that fitting a model for each choice of hyperparameters is costly, it is arguably wasteful to "throw away" all but the best result, as per Bayesian optimization. A related issue is the danger of overfitting the validation data when optimizing many hyperparameters. In this paper, we consider an alternative approach that uses more samples from the hyperparameter selection procedure to average over the uncertainty in model hyperparameters. The resulting approach, empirical Bayes for hyperparameter averaging (EB-Hyp) predicts held-out data better than Bayesian optimization in two experiments on latent Dirichlet allocation and deep latent Gaussian models. EB-Hyp suggests a simpler approach to evaluating and deploying machine learning algorithms that does not require a separate validation data set and hyperparameter selection procedure.
We establish the first general connection between the design of quantum algorithms and circuit lower bounds. Specifically, let C be a class of polynomialsize concepts, and suppose that C can be PAC-learned with member...
详细信息
ISBN:
(纸本)9781665420556
We establish the first general connection between the design of quantum algorithms and circuit lower bounds. Specifically, let C be a class of polynomialsize concepts, and suppose that C can be PAC-learned with membership queries under the uniform distribution with error 1/2 - gamma by a time T quantum algorithm. We prove that if gamma(2) center dot T << 2(n)/n, then BQE not subset of C, where BQE = BQTIME[2(O(n))] is an exponential-time analogue of BQP. This result is optimal in both gamma and T, since it is not hard to learn any class C of functions in (classical) time T = 2(n) (with no error), or in quantum time T = poly(n) with error at most 1/2 - Omega(2(-n/2)) via Fourier sampling. In other words, even a marginal quantum speedup over these generic learning algorithms would lead to major consequences in complexity lower bounds. As a consequence, our result shows that the study of quantum learning speedups is intimately connected to fundamental open problems about algorithms, quantum computing, and complexity theory. Our proof builds on several works in learning theory, pseudorandomness, and computational complexity, and on a connection between non-trivial classical learning algorithms and circuit lower bounds established by Oliveira and Santhanam (CCC 2017). Extending their approach to quantum learning algorithms turns out to create significant challenges, since extracting computational hardness from a quantum computation is inherently more complicated. To achieve that, we show among other results how pseudorandom generators imply learning-to-lower-bound connections in a generic fashion, construct the first conditional pseudorandom generator secure against uniform quantum computations, and extend the local list-decoding algorithm of Impagliazzo, Jaiswal, Kabanets and Wigderson (SICOMP 2010) to quantum circuits via a delicate analysis. We believe that these contributions are of independent interest and might find other applications.
In this work, we proposed the use of Support Vector Machines (SVM) to predict the performance of machine learning algorithms based on features of the learning problems. This work is related to the Meta-Regression appr...
详细信息
ISBN:
(纸本)9783540875352
In this work, we proposed the use of Support Vector Machines (SVM) to predict the performance of machine learning algorithms based on features of the learning problems. This work is related to the Meta-Regression approach, which has been successfully applied to predict learning performance, supporting algorithm selection. Experiments were performed in a case study in which SVMs with different kernel functions were used to predict the performance of Multi-Layer Perceptron (MLP) networks. The SVMs obtained better results in the evaluated task, when compared to different algorithms that have been applied as meta-regressors in previous work.
The time-consuming search for parking lots could be assisted by efficient routing systems. Still, the needed vacancy detection is either very hardware expensive, lacks detail or does not scale well for industrial appl...
详细信息
ISBN:
(纸本)9781479919598
The time-consuming search for parking lots could be assisted by efficient routing systems. Still, the needed vacancy detection is either very hardware expensive, lacks detail or does not scale well for industrial application. This paper presents a video-based system for cost-effective detection of vacant parking lots, and an extensive evaluation with respect to the system's transferability to unseen environments. Therefore, different image features and learning algorithms were examined on three independent datasets for an unbiased validation. A feature/classifier combination which solved the given task against the background of a robustly scalable system, which does not require re-training on new parking areas, was found. In addition, the best feature provides high performance on gray value surveillance cameras. The final system reached an accuracy of 92.33 % to 99.96 %, depending on the parking rows' distance, using DoG-features and a support vector machine.
There has been a steady surge in various sub-fields of machine learning where the focus is on developing systems that learn in an open-ended manner. This is particularly visible in the fields of language grounding and...
详细信息
ISBN:
(纸本)9781467366984
There has been a steady surge in various sub-fields of machine learning where the focus is on developing systems that learn in an open-ended manner. This is particularly visible in the fields of language grounding and data stream learning. These systems are designed to evolve as new data arrive, modifying and adjusting learned categories, as well as, accommodating new categories. Although some of the features of incremental learning are present in open-ended learning, the latter can not be characterized as standard incremental learning. This paper presents and discusses the key characteristics of open-ended learning, differentiating it from the standard incremental approaches. The main contribution of this paper is concerned with the evaluation of these algorithms. Typically, the performance of learning algorithms is assessed using traditional train-test methods, such as holdout, cross-validation etc. These evaluation methods are not suited for applications where environments and tasks can change and therefore the learning system is frequently facing new categories. To address this, a well defined and practical protocol is proposed. The utility of the protocol is demonstrated by evaluating and comparing a set of learning algorithms at the task of open-ended visual category learning.
This paper presents two novel Bayesian learning recovery algorithms for block sparse signals. Two cases are considered. In the first case, the signals within each block are correlated and the block borders are known. ...
详细信息
ISBN:
(纸本)9781665482370
This paper presents two novel Bayesian learning recovery algorithms for block sparse signals. Two cases are considered. In the first case, the signals within each block are correlated and the block borders are known. In the second case, the block borders are unknown and the signal elements are uncorrelated. Unlike their existing counterparts, the proposed algorithms obtain the optimal block covariances from the data estimated in the previous iterations. Furthermore, the decision to declare a block as zero is based on hypothesis testing. For the second case, we introduce a new prior model which is characterized by elastic dependencies among neighbouring signal elements. Using this model, we develop a novel Bayesian learning algorithm which iterates between estimating the dependencies among the signal elements and updating the Gaussian prior model. Numerical simulations illustrate the effectiveness of the proposed algorithms.
作者：
Uehara, KKobe Univ
Res Ctr Urban Safety & Secur Nada Ku Kobe Hyogo 6578501 Japan
In machine learning, it is important to reduce computational time to analyze learning algorithms. Some researchers have attempted to understand learning algorithms by experimenting them on a variety of domains. Others...
详细信息
ISBN:
(纸本)3540653902
In machine learning, it is important to reduce computational time to analyze learning algorithms. Some researchers have attempted to understand learning algorithms by experimenting them on a variety of domains. Others have presented theoretical methods of learning algorithm by using approximately mathematical model. The mathematical model has some deficiency that, if the model is too simplified, it may lose the essential behavior of the original algorithm. Furthermore, experimental analyses are based only on informal analyses of the learning task, whereas theoretical analyses address the worst case. Therefore, the results of theoretical analyses are quite different from empirical results. In our framework, called random case analysis, we adopt the idea of randomized algorithms. By using random case analysis, it can predict various aspects of learning algorithm's behavior, and require less computational time than the other theoretical analyses. Furthermore, we can easily apply our framework to practical learning algorithms.
Experimentation of new algorithms is the usual companion section of papers dealing with SAT. However, the behavior of those algorithms is so unpredictable that even strong experiments (hundreds of benchmarks. dozen of...
详细信息
ISBN:
(纸本)9783540859574
Experimentation of new algorithms is the usual companion section of papers dealing with SAT. However, the behavior of those algorithms is so unpredictable that even strong experiments (hundreds of benchmarks. dozen of solvers) can be still misleading. We present here a set of experiments of very small changes of a canonical Conflict Driven Clause learning (CDCL) solver and show that even very close versions can lead to very different behaviors. In some cases, the best of them could perfectly have been used to convince the reader of the efficiency of a new method for SAT. This observation can be explained by the lack of real experimental studies of CDCL solvers.
暂无评论