Learn More
We trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. This end-to-end approach proved surprisingly powerful. With minimum training data from humans the system learns to drive in traffic on local roads with or without lane markings and on highways. It also operates in areas with(More)
Our objective is to speed up non-linear SVM prediction while maintaining classification accuracy above an acceptable limit. We generalize Localized Multiple Kernel Learning so as to learn a tree-based primal feature embedding which is high dimensional and sparse. Primal based classification decouples prediction costs from the number of support vectors and(More)
Lifted inference algorithms for probabilistic first-order logic frameworks such as Markov logic networks (MLNs) have received significant attention in recent years. These algorithms use so called lifting rules to identify symmetries in the first-order representation and reduce the inference problem over a large probabilistic model to an inference problem(More)
This paper studies a new framework for learning a predictor in the presence of multiple kernel functions where the learner selects or extracts several kernel functions from potentially complex families and finds an accurate predictor defined in terms of these functions. We present an algorithm , Voted Kernel Regularization, that provides the flexibility of(More)
The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich repre-sentational power of neural networks with Bayesian methods. However, most work on VAEs use a rather simple prior over the latent variables such as standard normal distribution , thereby restricting its applications to relatively simple(More)
Support Vector Machines (SVMs) are state-of-the-art algorithms for classification in machine learning. However, the SVM formulation does not directly seek to find sparse solutions. In this work, we propose an alternate formulation that explicitly imposes sparsity. We show that the proposed technique is related to the standard SVM formulation and therefore(More)