Unsupervised Learning by Program Synthesis

By Kevin Ellis, Armando Solar-Lezama, Josh Tenenbaum. 2015

81 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A Compositional Object-Based Approach to Learning Physical Dynamics (2016, methodology): “This approach of starting with a general sketch of a program and ﬁlling in the speciﬁcs is inspired by ideas from the program synthesis community (Ellis et al., 2015; Gaunt et al., 2016; Solar-Lezama, 2008).”
TerpreT: A Probabilistic Programming Language for Program Induction (2016, methodology): “synthesis algorithm (Singh, 2016), and synthesizing programs without any examples by performing a joint inference over the program and the inputs to recover compressed encodings of the observed data (Ellis et al., 2015). In this work,we are targeting speciﬁcations based on input-output examples as t”
Learning to Infer and Execute 3D Shape Programs (2019, methodology): “(2018) leveraged symbolic program synthesis techniques to infer 2D graphics programs from images, extending their earlier work by using neural nets for faster inference of low-level cues such as strokes (Ellis et al., 2015).”
Learning Interpretable Models with Causal Guarantees (2019, unknown): “…Rudin, 2016), generalized additive models (Lou et al., 2012; Caruana et al., 2015), rule lists (Wang and Rudin, 2015; Yang et al., 2017; Angelino et al., 2017), decision sets (Lakkaraju et al., 2016), and programs (Ellis et al., 2015; Verma et al., 2018; Valkov et al., 2018; Ellis et al., 2018).”
Not-So-CLEVR: learning same–different relations strains feedforward neural networks (2018, methodology): “recent work has shown how CNNs, including variants of the popular LeNet [6] and AlexNet [7] architectures, could only solve a handful of the 23 SVRT problems [8,9].”
Learning to Infer Graphics Programs from Hand-Drawn Images (2017, methodology): “The goals of [8] were cognitive modeling, and they applied their technique to synthetic scenes used in human behavioral studies.”
Learning Relational Representations with Auto-encoding Logic Programs (2019, methodology): “We draw inspiration from program induction and synthesis [Gulwani et al. , 2017], in particular, unsupervised meth-ods for program induction [Ellis et al. , 2015; Lake et al. , 2015].”