Results

**1 - 3**of**3**### Deep Knowledge: Inductive Programming as an Answer

, 2013

"... Inductive programming has focussed on problems where data are not necessarily big, but representation and patterns may be deep (including recursion and complex structures). In this context, we will discuss what really makes some problems hard and whether this difficulty is related to what humans con ..."

Abstract
- Add to MetaCart

(Show Context)
Inductive programming has focussed on problems where data are not necessarily big, but representation and patterns may be deep (including recursion and complex structures). In this context, we will discuss what really makes some problems hard and whether this difficulty is related to what humans consider hard. We will highlight the relevance of background knowledge in this difficulty and how this has influence on a preference of inferring small hypotheses that are added incrementally. When dealing with the techniques to acquire, maintain, revise and use this knowledge, we argue that symbolic approaches (featuring powerful construction, abstraction and/or higher-order features) have several advantages over non-symbolic approaches, especially when knowledge becomes complex. Also, inductive programming hypotheses (in contrast to many other machine learning paradigms) are usually related to the solutions that humans would find for the same problem, as the constructs that are given as background knowledge are explicit and shared by users and the inductive programming system. This makes inductive programming a very appropriate paradigm for addressing and better understanding many challenging problems humans can solve but ma-chines are still struggling with. Some important issues for the discussion will be the relevance of pattern intelligibility, and the concept of scalability in terms of incrementality, learning to learn, constructive induction, bias, etc.

### Synthesis of Functions Using Generic Programming

"... Abstract. This paper describes a very flexible way to synthesize functions matching a given predicate. This can be used to find general recursive functions or λ-terms obeying an input–output behavior specified by a number of examples. Generating complex algorithms from just a small number of simple ..."

Abstract
- Add to MetaCart

(Show Context)
Abstract. This paper describes a very flexible way to synthesize functions matching a given predicate. This can be used to find general recursive functions or λ-terms obeying an input–output behavior specified by a number of examples. Generating complex algorithms from just a small number of simple input-output pairs is the goal of inductive programming. This paper illustrates that our approach works well in some challenging examples. 1

### Learning Probabilistic Programs

"... We develop a technique for generalising from data in which models are samplers represented as program text. We establish encouraging empirical results that sug-gest that Markov chain Monte Carlo probabilistic programming inference tech-niques coupled with higher-order probabilistic programming langu ..."

Abstract
- Add to MetaCart

(Show Context)
We develop a technique for generalising from data in which models are samplers represented as program text. We establish encouraging empirical results that sug-gest that Markov chain Monte Carlo probabilistic programming inference tech-niques coupled with higher-order probabilistic programming languages are now sufficiently powerful to enable successful inference of this kind in nontrivial do-mains. We also introduce a new notion of probabilistic program compilation and show how the same machinery might be used in the future to compile probabilistic programs for efficient reusable predictive inference. 1