7 accepted papers
The information bottleneck principle provides an information-theoretic method for representation learning, by training an encoder to retain all information which is relevant for predicting the label while minimizing the amount of other, excess information in the representation. The original formulat…
We present a method for feature interpretation that makes use of recent advances in autoregressive density estimation models to invert model representations. We train generative inversion models to express a distribution over input features conditioned on intermediate model representations. Insights…
Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this type of attack. In this paper, we propose a new class of adversarial examples that are synthesized entirely from scratch us…
Adversarial perturbations of normal images are usually imperceptible to humans, but they can seriously confuse state-of-the-art machine learning models. What makes them so special in the eyes of image classifiers? In this paper, we show empirically that adversarial examples mainly lie in the low pro…
We develop a framework for combining differentiable programming languages with neural networks. Using this framework we create end-to-end trainable systems that learn to write interpretable algorithms with perceptual components. We explore the benefits of inductive biases for strong generalization a…
We introduce and develop solutions for the problem of Lifelong Perceptual Programming By Example (LPPBE). The problem is to induce a series of programs that require understanding perceptual data like images or text. LPPBE systems learn from weak supervision (input-output examples) and incrementally…
We propose the Neural Program Lattice (NPL), a neural network that learns to perform complex tasks by composing low-level programs to express high-level programs. Our starting point is the recent work on Neural Programmer-Interpreters (NPI), which can only learn from strong supervision that contains…