Search Results for author:
Found 11 papers, 6 papers with code
DeepDrummer : Generating Drum Loops using Deep Learning and a Human in the Loop
DeepDrummer is a drum loop generation tool that uses active learning to learn the preferences (or current artistic intentions) of a human user from a small number of interactions.
Robo-PlaNet: Learning to Poke in a Day
Recently, the Deep Planning Network (PlaNet) approach was introduced as a model-based reinforcement learning method that learns environment dynamics directly from pixel observations.
Negative eigenvalues of the Hessian in deep neural networks
The loss function of deep networks is known to be non-convex but the precise nature of this nonconvexity is still an active area of research.
Understanding intermediate layers using linear classifier probes
Neural network models have a reputation for being black boxes.
Theano: A Python framework for fast computation of mathematical expressions
Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.
Variance Reduction in SGD by Distributed Importance Sampling
This leads the model to update using an unbiased estimate of the gradient which also has minimum variance when the sampling proposal is proportional to the L2-norm of the gradient.
GSNs : Generative Stochastic Networks
We introduce a novel training principle for probabilistic models that is an alternative to maximum likelihood.
Techniques for Learning Binary Stochastic Feedforward Neural Networks
Our experiments confirm that training stochastic networks is difficult and show that the proposed two estimators perform favorably among all the five known estimators.
Deep Generative Stochastic Networks Trainable by Backprop
We introduce a novel training principle for probabilistic models that is an alternative to maximum likelihood.
Generalized Denoising Auto-Encoders as Generative Models
Recent work has shown how denoising and contractive autoencoders implicitly capture the structure of the data-generating density, in the case where the corruption noise is Gaussian, the reconstruction error is the squared error, and the data is continuous-valued.
What Regularized Auto-Encoders Learn from the Data Generating Distribution
This paper clarifies some of these previous observations by showing that minimizing a particular form of regularized reconstruction error yields a reconstruction function that locally characterizes the shape of the data generating density.
