Reverse engineering of binary executables is a critical problem in the computer security domain.

Neural Information Processing Systems http://nips.cc/

We present a unified framework for learning continuous control policies using backpropagation. It supports stochastic control by treating stochasticity in the Bellman equation as a deterministic function of exogenous noise. The product is a spectrum of general policy gradient algorithms that range from model-free methods with value functions to model-based methods without value functions. We use learned models but only require observations from the environment instead of observations from model-predicted trajectories, minimizing the impact of compounded model errors. We apply these algorithms first to a toy stochastic control problem and then to several physics-based control problems in simulation. One of these variants, SVG(1), shows the effectiveness of learning models, value functions, and policies simultaneously in continuous domains.

Restricted Boltzmann machines are undirected neural networks which have been shown to be effective in many applications, including serving as initializations for training deep multi-layer neural networks. One of the main reasons for their success is the existence of efficient and practical stochastic algorithms, such as contrastive divergence, for unsupervised training. We propose an alternative deterministic iterative procedure based on an improved mean field method from statistical physics known as the Thouless-Anderson-Palmer approach. We demonstrate that our algorithm provides performance equal to, and sometimes superior to, persistent contrastive divergence, while also providing a clear and easy to evaluate objective function. We believe that this strategy can be easily generalized to other models as well as to more accurate higher-order approximations, paving the way for systematic improvements in training Boltzmann machines with hidden units.

Neural Information Processing Systems http://nips.cc/

In tabular grid worlds, object locations are randomised across lifetimes but fixed within a lifetime. There are two different action spaces. The other version has only 9 movement actions. The episode terminates after a fixed number of steps (i.e., chain length), which is There is no state aliasing because all states are distinct. We trained LPGs by simulating 960 parallel lifetimes (i.e., batch size for meta-gradients), each of Rectified linear unit (ReLU) was used as activation function throughout the experiment.

Neural Information Processing Systems http://nips.cc/

We present a simple and effective approach for non-blind image deblurring, combining classical techniques and deep learning.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/