Abstract We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than

-differences t test based on 10-fold cross-validation, exhibits somewhat elevated probability of type I error. A fourth test, McNemar’s test, is shown to have low type I error. The fifth test is a new test, 5 × 2 cv, based on five iterations of twofold cross-validation. Experiments show that this test also has

and learns a Support Vector Machine classifier with kernels based on two effective measures for comparing distributions, the Earth Mover’s Distance and the χ 2 distance. We first evaluate the performance of our approach with different keypoint detectors and descriptors, as well as different kernels

Here we continue the analytic study of packet switching in radio channels which we reported upon in our two previous papers [ 11, [2]. Again we consider a population of terminals communicating with a central station over a packet-switched radio channel. The allocation of bandwidth among

We propose a new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. We take an object recognition approach, designing an intermediate body parts representation that maps the difficult pose estimation problem into a simpler

Recently SVMs using spatial pyramid matching (SPM) kernel have been highly successful in image classification. Despite its popularity, these nonlinear SVMs have a complexity O(n 2 ∼ n 3) in training and O(n) in testing, where n is the training size, implying that it is nontrivial to scaleup

The classification rules induced by machine learning systems are judged by two criteria: their classification accuracy on an independent test set (henceforth "accuracy"), and their complexity. The relationship between these two criteria is, of course, of keen interest

Systems for inducing concept descriptions from examples are valuable tools for assisting in the task of knowledge acquisition for expert systems. This paper presents a description and empirical evaluation of a new induction system, cn2, designed for the efficient induction of simple

between robots R1 and R2 in the situation depicted in Figure 1(a), but also that in Figure 1(b), which is typically not considered as a collision in existing multi-robot systems. (a) (b) (c) Figure 2: Illustration of deadloop. The green square and the red square are the robot positions and the goal

(MD), which has been widely used in the past for studying simple liquids and solids, has more recently been applied to molecular systems with internal degrees of freedom such as N, [l], H,O [2] and even C,H,, [3]. In applying the MD method three problems arise: (a) the choice of a suitable mechanical