Search Results for author:
Found 8 papers, 0 papers with code
Stretched sinograms for limited-angle tomographic reconstruction with neural networks
We compare our method to using a U-Net to directly reconstruct the unstretched tilt views and show that this simple stretching procedure leads to significantly better reconstructions.
Online approximate factorization of a kernel matrix by a Hebbian neural network
Minimizing this upper bound leads to a minimax optimization, which can be solved via stochastic gradient descent-ascent.
QXplore: Q-Learning Exploration by Maximizing Temporal Difference Error
We implement the objective with an adversarial Q-learning method in which Q and Qx are the action-value functions for extrinsic and secondary rewards, respectively.
Reward Prediction Error as an Exploration Objective in Deep RL
We then propose a deep reinforcement learning method, QXplore, which exploits the temporal difference error of a Q-function to solve hard exploration tasks in high-dimensional MDPs.
Q-Learning for Continuous Actions with Cross-Entropy Guided Policies
CGP aims to combine the stability and performance of iterative sampling policies with the low computational cost of a policy network.
Program Synthesis Through Reinforcement Learning Guided Tree Search
Program Synthesis is the task of generating a program from a provided specification.
Maximin affinity learning of image segmentation
We present the first machine learning algorithm for training a classifier to produce affinity graphs that are good in the sense of producing segmentations that directly minimize the Rand index, a well known segmentation performance measure.
Natural Image Denoising with Convolutional Networks
We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedure that synthesizes training samples from specific noise models.
