Learning Program Synthesis for Integer Sequences from Scratch
نویسندگان
چکیده
We present a self-learning approach for synthesizing programs from integer sequences. Our method relies on tree search guided by learned policy. system is tested the On-Line Encyclopedia of Integer Sequences. There, it discovers, its own, solutions 27987 sequences starting basic operators and without human-written training examples.
منابع مشابه
Learning Face Representation from Scratch
Pushing by big data and deep convolutional neural network (CNN), the performance of face recognition is becoming comparable to human. Using private large scale training datasets, several groups achieve very high performance on LFW, i.e., 97% to 99%. While there are many open source implementations of CNN, none of large scale face dataset is publicly available. The current situation in the field...
متن کاملLearning to Align from Scratch
Unsupervised joint alignment of images has been demonstrated to improve performance on recognition tasks such as face verification. Such alignment reduces undesired variability due to factors such as pose, while only requiring weak supervision in the form of poorly aligned examples. However, prior work on unsupervised alignment of complex, real-world images has required the careful selection of...
متن کاملInteger Sequences from Queueing Theory
Moment sequences associated with probability distributions can be sources of integer sequences. Operators on probability distributions correspond to operators on integer sequences. Thus, there is an opportunity to apply each theory to the other. Moreover, probability models can be sources of integer sequences, both classical and new, as we show by considering the classical M/G/1 single-server q...
متن کاملIdentity Synthesis: Creating An Identity From Scratch
A substantial quantity of research has previously been conducted into the identification and application of measures related to the detection and prevention of identity theft and identity fraud. In the current security conscious environment, the concept of creating an artificial identity is generally met with both caution and suspicion. Much of the attention placed on the concept of identity fa...
متن کاملLearning model-based planning from scratch
Conventional wisdom holds that model-based planning is a powerful approach to sequential decision-making. It is often very challenging in practice, however, because while a model can be used to evaluate a plan, it does not prescribe how to construct a plan. Here we introduce the “Imagination-based Planner”, the first model-based, sequential decision-making agent that can learn to construct, eva...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence
سال: 2023
ISSN: ['2159-5399', '2374-3468']
DOI: https://doi.org/10.1609/aaai.v37i6.25930