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

Part 3: Innovation in Clinical Research: AI-based Drug Development Tools and the Regulatory Landscape‍

Webinars

Part 2: Faster, More Efficient Trials: Novel Trial Designs using Digital Twins‍

Webinars

Part 1: AI, Digital Twins, and the Future of Clinical Research‍

Learn about how Digital Twins are created and how they are incorporated into clinical trials to increase power, accelerate timelines, and enable patient level insights.
Watch an overview of specific use cases for Digital Twins and learn how novel trial designs with Digital Twins enable smaller trials that maintain their power.
Watch a panel discussion on the regulatory landscape where experts share perspectives on the future of AI-based drug development tools like Digital Twins.