Timezone: »

 
Poster
Deep symbolic regression for recurrence prediction
Stéphane d'Ascoli · Pierre-Alexandre Kamienny · Guillaume Lample · Francois Charton

Wed Jul 20 03:30 PM -- 05:30 PM (PDT) @ Hall E #433
in Poster Session 2 »
Symbolic regression, i.e. predicting a function from the observation of its values, is well-known to be a challenging task. In this paper, we train Transformers to infer the function or recurrence relation underlying sequences of integers or floats, a typical task in human IQ tests which has hardly been tackled in the machine learning literature. We evaluate our integer model on a subset of OEIS sequences, and show that it outperforms built-in Mathematica functions for recurrence prediction. We also demonstrate that our float model is able to yield informative approximations of out-of-vocabulary functions and constants, e.g. $\operatorname{bessel0}(x)\approx \frac{\sin(x)+\cos(x)}{\sqrt{\pi x}}$ and $1.644934\approx \pi^2/6$.
Keywords: APP: Time Series · DL: Algorithms · DL: Attention Mechanisms · DL: Everything Else · DL: Sequential Models, Time series

Author Information

Stéphane d'Ascoli (ENS / FAIR, Paris)
Pierre-Alexandre Kamienny (Facebook)
Guillaume Lample (Facebook AI Research)
Francois Charton (FAIR)

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

More from the Same Authors