Latest YouTube Video

Monday, July 18, 2016

Backprop KF: Learning Discriminative Deterministic State Estimators. (arXiv:1605.07148v2 [cs.LG] UPDATED)

Generative state estimators based on probabilistic filters and smoothers are one of the most popular classes of state estimators for robots and autonomous vehicles. However, generative models have limited capacity to handle rich sensory observations, such as camera images, since they must model the entire distribution over sensor readings. Discriminative models do not suffer from this limitation, but are typically more complex to train as latent variable models for state estimation. We present an alternative approach where the parameters of the latent state distribution are directly optimized as a deterministic computation graph, resulting in a simple and effective gradient descent algorithm for training discriminative state estimators. We show that this procedure can be used to train state estimators that use complex input, such as raw camera images, which must be processed using expressive nonlinear function approximators such as convolutional neural networks. Our model can be viewed as a type of recurrent neural network, and the connection to probabilistic filtering allows us to design a network architecture that is particularly well suited for state estimation. We evaluate our approach on synthetic tracking task with raw image inputs and on the visual odometry task in the KITTI dataset. The results show significant improvement over both standard generative approaches and regular recurrent neural networks.



from cs.AI updates on arXiv.org http://ift.tt/1Ua9rII
via IFTTT

Performance Based Evaluation of Various Machine Learning Classification Techniques for Chronic Kidney Disease Diagnosis. (arXiv:1606.09581v2 [cs.LG] UPDATED)

Areas where Artificial Intelligence (AI) & related fields are finding their applications are increasing day by day, moving from core areas of computer science they are finding their applications in various other domains.In recent times Machine Learning i.e. a sub-domain of AI has been widely used in order to assist medical experts and doctors in the prediction, diagnosis and prognosis of various diseases and other medical disorders. In this manuscript the authors applied various machine learning algorithms to a problem in the domain of medical diagnosis and analyzed their efficiency in predicting the results. The problem selected for the study is the diagnosis of the Chronic Kidney Disease.The dataset used for the study consists of 400 instances and 24 attributes. The authors evaluated 12 classification techniques by applying them to the Chronic Kidney Disease data. In order to calculate efficiency, results of the prediction by candidate methods were compared with the actual medical results of the subject.The various metrics used for performance evaluation are predictive accuracy, precision, sensitivity and specificity. The results indicate that decision-tree performed best with nearly the accuracy of 98.6%, sensitivity of 0.9720, precision of 1 and specificity of 1.



from cs.AI updates on arXiv.org http://ift.tt/29hkh2t
via IFTTT

video not showing up for anonymous

Here is my setup: - A media entity with a bundle containing a video_embed field - A node with an entity ref field pointing to this media bundle.

from Google Alert - anonymous http://ift.tt/2a68WCy
via IFTTT

Anonymous ex-Turkish officer claims rebel jets had Erdogan's plane in their sights, didn't open fire

At the height of the attempt to overthrow Turkish President Tayyip Erdogan, the rebel pilots of two F-16 fighter jets had Erdogan's plane in their sights.

from Google Alert - anonymous http://ift.tt/2aoFeVK
via IFTTT

Orioles: 1B Chris Davis (illness) out of lineup for Monday's game vs. Yankees after spending the night in hospital (ESPN)

from ESPN http://ift.tt/1eW1vUH
via IFTTT