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.

Enter your email address to watch the webinar.

Click the link to watch webinar.
Oops! Something went wrong while submitting the form.
Webinars

How will AI transform the future of medicine?

White Papers

Evaluating Digital Twins for Alzheimer’s Disease using Data from a Completed Phase 2 Clinical Trial

White Papers

Prognostic digital twins overcome the limitations of external control arms in RCTs

Both methods reduce control arm sizes, but only digital twins control for bias.
A Phase 2 study on crenezumab in mild-to-moderate AD was used to retrospectively assess the validity of Unlearn's approach for AD clinical trials.
Hear from Charles Fisher, founder and CEO of Unlearn, in this on-demand webinar about how AI will transform the medical landscape of tomorrow.