The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names. However, this proves to be a difficult task due to dominance of non-visual semantics in underlying vector-space embeddings of class names. To address this issue, we discriminatively...
In many computer vision tasks, for example saliency prediction or semantic segmentation, the desired output is a foreground map that predicts pixels where some criteria is satisfied. Despite the inherently spatial nature of this task commonly used learning objectives do not incorporate the spatial relationships between misclassified pixels and the underlying ground truth. The Weighted F-measure, a...
We aim to tackle a novel vision task called Weakly Supervised Visual Relation Detection (WSVRD) to detect “subject-predicate-object” relations in an image with object relation groundtruths available only at the image level. This is motivated by the fact that it is extremely expensive to label the combinatorial relations between objects at the instance level. Compared to the extensively studied problem,...
We study the task of unsupervised domain adaptation, where no labeled data from the target domain is provided during training time. To deal with the potential discrepancy between the source and target distributions, both in features and labels, we exploit a copula-based regression framework. The benefits of this approach are two-fold: (a) it allows us to model a broader range of conditional predictive...
The Particle Swarm Optimization Policy (PSO-P) has been recently introduced and proven to produce remarkable results on interacting with academic reinforcement learning benchmarks in an off-policy, batch-based setting. To further investigate the properties and feasibility on real-world applications, this paper investigates PSO-P on the so-called Industrial Benchmark (IB), a novel reinforcement learning...
We explore the use of synthetic benchmarks for the training phase of machine-learning-based automatic performance tuning. We focus on the problem of predicting if the use of local memory on a GPU is beneficial for caching a single target array in a GPU kernel. We show that the use of only 13 real benchmarks leads to poor prediction accuracy (about to 58%) of the 13 leave-one-out models trained using...
Predictive modeling using machine learning is an effective method for building compiler heuristics, but there is a shortage of benchmarks. Typical machine learning experiments outside of the compilation field train over thousands or millions of examples. In machine learning for compilers, however, there are typically only a few dozen common benchmarks available. This limits the quality of learned...
Fast and efficient design space exploration is a critical requirement for designing computer systems, however, the growing complexity of hardware/software systems and significantly long run-times of detailed simulators often makes it challenging. Machine learning (ML) models have been proposed as popular alternatives that enable fast exploratory studies. The accuracy of any ML model depends heavily...
Design Space Exploration (DSE) is a critical step in the chip design. The tradeoffs and interactions among parameters are traditionally evaluated by simulating or synthesizing a variety of designs which is intractable. The predictive modeling techniques have been applied to predict the design performance for DSE. For the system-on-a-chip (SoC) DSE cases, however, it is difficult to achieve high accuracy...
Active learning aims to selectively label the most informative examples to save the data collection cost. While active learning has been well studied for balanced classification problems, limited research is performed in cost-sensitive scenario. In this paper, we investigate the problem of active learning for cost-sensitive classification. We first propose a general active learning framework named...
Different applications have different memory and computational demands. Therefore, obtainable performance and energy efficiency on a GPU depends on how well the GPU resources and application demands are balanced. In this study, we are presenting a Neural Network based predictor to model power and performance of GPGPU applications. The proposed model accurately predicts power and performance for most...
This paper proposes a canonical correlation analysis (CCA) based workload-performance-resource (WPR) model which can capture and compare the complex many-to-many workload, performance and resource consumption relationship of an application running in physical and in virtual machines. The model can also establish complex relationships of the usage variables of four potentially interrelating resources...
Forecasting daily returns volatility is crucial in finance. Traditionally, volatility is modelled using a time-series of lagged information only, an approach which is in essence atheoretical. Although the relationship of market conditions and volatility has been studied for decades, we still lack a clear theoretical framework to allow us to forecast volatility, despite having many plausible explanatory...
In this paper, we propose linear branch entropy, a new metric for characterizing branch behavior. The metric is independent of the configuration of a specific branch predictor, but it is highly correlated with the branch miss rate of any predictor. In particular, we show that there is a linear relationship between linear branch entropy and the branch miss rate. This means that the metric can be used...
Graphics processing units (GPUs) can deliver considerable performance gains over general purpose processors. However, GPU performance improvement vary considerably across applications. Porting applications to GPUs by rewriting code with GPU-specific languages requires significant effort. In consequence, it is desirable to predict which applications would benefit most before porting to the GPU. This...
Adaptive program optimizations, such as automatic selection of the expected fastest implementation variant for a computation component depending on runtime context, are important especially for heterogeneous computing systems but require good performance models. Empirical performance models based on trial executions which require no or little human efforts show more practical feasibility if the sampling...
The growth of E-commerce which can be seen in recent years, has contributed a lot to global economy. Prediction of trade, especially in C2C market, can help decision-makers obtain the information from the online transactions and find the knowledge underlying the data. This paper facilities the traditional search index prediction system with ANFIS model. By using purchasing transactions from Taobao,...
Compilation optimization is critical for software performance. Before a product releases, the most effective algorithm combination should be chosen to minimize the object file size or to maximize the running speed. Compilers like GCC usually have hundreds of optimization algorithms, in which they have complex relationships. Different combinations of algorithms will lead to object files with different...
Architectural Design Space Exploration (DSE) is a notoriously difficult problem due to the exponentially large size of the design space and long simulation times. Previously, many studies proposed to formulate DSE as a regression problem which predicts architecture responses (e.g., time, power) of a given architectural configuration. Several of these techniques achieve high accuracy, though often...
Building effective optimization heuristics is a challenging task which often takes developers several months if not years to complete. Predictive modelling has recently emerged as a promising solution, automatically constructing heuristics from training data, however, obtaining this data can take months per platform. This is becoming an ever more critical problem as the pace of change in architecture...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.