Timezone: »

Differentiable Programs with Neural Libraries
Alex Gaunt · Marc Brockschmidt · Nate Kushman · Daniel Tarlow

Tue Aug 08 01:30 AM -- 05:00 AM (PDT) @ Gallery #134

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 and modularity that come from the program-like structure of our models. In particular, modularity allows us to learn a library of (neural) functions which grows and improves as more tasks are solved. Empirically, we show that this leads to lifelong learning systems that transfer knowledge to new tasks more effectively than baselines.

Author Information

Alex Gaunt (Microsoft)
Marc Brockschmidt (Microsoft Research)
Nate Kushman (Microsoft Research)
Daniel Tarlow (Google Brain)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors