This paper compares the performance of several classiier algorithms on a standard database of handwritten digits. We consider not only raw accuracy, but also rejection, training time, recognition time, and memory requirements.
Revisions to DSM-III cite apprehensive expectation or 'worry' as a defining feature of generalized anxiety disorder (GAD). The quality and focus of worry reported by groups of GAD patients (n = 19), and nonanxious 'controls' (n = 26) were examined using self-monitored data. Content categorizations by independent raters showed that GAD patients worried more… (More)
Research teams use common robots and machine learning to teach the robots outdoor navigation and locomotion skills.
Due to the technology available, most previous work in teleoperated robotics used relatively low-resolution video links and provided limited perceptual feedback to the teleoperator. In most cases, these projects reported only limited teleoperator success compared to vehicles with human drivers on-board. We set out to build a high-fidelity teleoperation… (More)
This paper proposes a new method, that we call Visu-alBackProp, for visualizing which sets of pixels of the input image contribute most to the predictions made by the convo-lutional neural network (CNN). The method heavily hinges on exploring the intuition that the feature maps contain less and less irrelevant information to the prediction decision when… (More)
This paper compares the performance of several classifier algorithms on a standard database of handwritten digits. We consider not only raw accuracy, but also rejection, training time, recognition time, and memory requirements.