I’m Neale Ratzlaff, 🌲 🌲 a Deep Learning and Computer Vision researcher, currently interning at Horizon Robotics, working on exploration in deep reinforcement learning
I’m a PhD candidate studying with Dr. Fuxin Li at Oregon State University. I’m broadly interested in implicit variational inference, generative models, uncertainty, and information geometry. It’s important to create AI agents which we can trust, meaning I spend a lot of time thinking about alignment and paperclips.
Currently I’m interested in learning distributions over functions, and using them to improve methods in computer vision and reinforcement learning. By leveraging some recent advances in particle vairational inference, we can learn these intractable distributions even for complex neural networks. The resulting distributions have numerous benefits over single models, and even bootstrapped ensembles.
I’ve worked at Horizon Robotics, Intel, and Tektronix
Implicit Generative Modeling for Efficient Exploration.
Ratzlaff, Bai, Fuxin, Xu (arxiv preprint) 2019
We model uncertainty estimation as an intrinsic reward for efficient exploration. We introduce an implicit generative modeling approach to estimate a Bayesian uncertainty of the agent’s belief of theenvironment dynamics. We approximate the posterior through multiple draws from our generative model. The variance of the dynamic models’ output is used as an intrinsic reward for exploration. We design a training algorithm for our generative model based on amortized Stein Variational Gradient Descent, to ensure the parameter distribution is a nontrivial approximation to the true posterior.
HyperGAN: A Generative Model for Diverse Performant Neural Networks.
Ratzlaff, Fuxin (ICML 2019)
Code: HyperGAN Github repo
Talk: ICML Oral Slideshare
We learn an implicit ensemble using a neural generating network. Trained by maximum likelihood, the generator learns to sample from the posterior of model parameters which fit the data. The generated model parameters achieve high accuracy, yet are distinct with different predictive distributions. We enforce diversity by regularizing the intermediate representations to be well-distributed, while not harming the flexibility of the output distribution.
Unifying Bilateral Filtering and Adversarial Training for Robust Neural Networks.
Ratzlaff, Fuxin (arxiv preprint) 2018
Code: Github repo
We use an adaptive bilateral filter to smooth the purturbations left by adversarial attacks. We view our method as a piecewise projection of the high frequency perturbations, back to the natural image manifold. Our method is simple, effective, and practical, unlike many other projection defenses
Methods for Detection and Recovery of Out-of-Distribution Examples. M.S. Degree Computer Science. Oregon State University (2018)
I maintain and work on various other projects, all deep learning related. Pretty much all of them are in PyTorch.
Inspired by Hardmaru, I build evolutionary creative machines. There is gallery of examples here