-
Synthesis of Differentiable Functional Programs for Lifelong Learning
We present a neurosymbolic approach to the lifelong learning of algorith...
read it
-
Learning to learn generative programs with Memoised Wake-Sleep
We study a class of neuro-symbolic generative models in which neural net...
read it
-
The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that lear...
read it
-
Transpiling Programmable Computable Functions to Answer Set Programs
Programming Computable Functions (PCF) is a simplified programming langu...
read it
-
General-purpose Declarative Inductive Programming with Domain-Specific Background Knowledge for Data Wrangling Automation
Given one or two examples, humans are good at understanding how to solve...
read it
-
First Experiments with PowerPlay
Like a scientist or a playing child, PowerPlay not only learns new skill...
read it
-
Augmenting Neural Nets with Symbolic Synthesis: Applications to Few-Shot Learning
We propose symbolic learning as extensions to standard inductive learnin...
read it
DreamCoder: Growing generalizable, interpretable knowledge with wake-sleep Bayesian program learning
Expert problem-solving is driven by powerful languages for thinking about problems and their solutions. Acquiring expertise means learning these languages – systems of concepts, alongside the skills to use them. We present DreamCoder, a system that learns to solve problems by writing programs. It builds expertise by creating programming languages for expressing domain concepts, together with neural networks to guide the search for programs within these languages. A “wake-sleep” learning algorithm alternately extends the language with new symbolic abstractions and trains the neural network on imagined and replayed problems. DreamCoder solves both classic inductive programming tasks and creative tasks such as drawing pictures and building scenes. It rediscovers the basics of modern functional programming, vector algebra and classical physics, including Newton's and Coulomb's laws. Concepts are built compositionally from those learned earlier, yielding multi-layered symbolic representations that are interpretable and transferrable to new tasks, while still growing scalably and flexibly with experience.
READ FULL TEXT
Comments
There are no comments yet.