Boltzmann Encoded Adversarial Machines

Restricted Boltzmann Machines (RBMs) are a class of generative neural network that are typically trained to maximize a log-likelihood objective function. We argue that likelihood-based training strategies may fail because the objective does not sufficiently penalize models that place a high probability in regions where the training data distribution has low probability. To overcome this problem, we introduce Boltzmann Encoded Adversarial Machines (BEAMs). A BEAM is an RBM trained against an adversary that uses the hidden layer activations of the RBM to discriminate between the training data and the probability distribution generated by the model. We present experiments demonstrating that BEAMs outperform RBMs and GANs on multiple benchmarks.

Enter your email address to download paper.

Click the link to begin download.
Oops! Something went wrong while submitting the form.
Blog

AD/PD 2021: Unlearn will present novel, AI-driven approaches to enabling smaller, more efficient Alzheimer’s clinical trials

Press

How Digital Twin Technology is Disrupting Healthcare

Press

Next-gen digital health innovation in clinical trials

The Rock Health team reflects on the evolution of digital in clinical trials, discuss the current state, and explore the opportunity to further transform drug discovery.
The use of digital twins in the healthcare industry is revolutionizing clinical processes.
Join us at The 15th​ International Conference on Alzheimer’s and Parkinson’s Diseases and related neurological disorders, March 9 - 14, 2021.