[paper reading][AI 2021] Making sense of sensory input
2021/11/7 23:19:05
本文主要是介绍[paper reading][AI 2021] Making sense of sensory input,对大家解决编程问题具有一定的参考价值,需要的程序猿们随着小编来一起学习吧!
目录- 1 Introduction
- 1.1 Related work
- 2 Background
- 3 A computational framework for making sense of sensory sequences
- 3.1 - 3.4
- 3.5 -
- 4 Computer implementation
- 6 Noisy apperception
- AI 2021
- https://www.sciencedirect.com/science/article/pii/S0004370220301855
- an ILP system for sequences. predict, retrodict, impute
- unsupervised program synthesis
- PI, object invention
- noised but low-dim inputs with only a few types of labels
1 Introduction
- symbolic theory
- explain, and unity
- causal language, \(Datalog^\ni\), generates a \(Datalog^\ni\) program
- relatively human-readable
- data-efficient
- elementary cellular automata, music, Seek Whence (sequences), multi-modal binding, occlusion
1.1 Related work
- model-based RL or MCTS
- accurate model of the game dynamics
- learning models
- three dimensions: latent? symbolic? prior?
- HMM
- only transition
- transition, perception, render
- ours: latent states, latent objects
- vectors: hard. symbols: relatively easy to understand
- some: state symbols, transition tensors
- prior: conv? event calculus? rules?
2 Background
- Datalog clause, interpreter in ASP
- subset-minimal Herbrand model
- ASP solvers, weak constraints
3 A computational framework for making sense of sensory sequences
3.1 - 3.4
- unambiguous symbolic sensory sequence
- theory, type, initial conditions, rules, constraints
- static rule, causal rule
- unary, binary, uniqueness constraint
- disallowing constants
- constraint, incompossible
- covered by
- example: three cycled states
- unity
- cost
3.5 -
- different interpretations
- trivial interpretation, upper bound
4 Computer implementation
- template, type signature, constants (static, causal, body atoms)
- increasing complexity
- lowest cost
- two non-trivial parts
- enumerate templates
- diagonalization, \((T,n)\) pairs
- infinite list of finite lists of: objects, predicates, variables
- find the best theory
- deduction, abduction, induction, combine (facts, rules, outputs)
- \(datalog^\ni\) interpreter in ASP
- ASP encoding, meta-interpreter
- complexity
- optimization
6 Noisy apperception
- length: increasing performance
- percentage of mislabelled data: decreasing performance
这篇关于[paper reading][AI 2021] Making sense of sensory input的文章就介绍到这儿,希望我们推荐的文章对大家有所帮助,也希望大家多多支持为之网!
- 2024-11-20实战:30 行代码做一个网页端的 AI 聊天助手
- 2024-11-185分钟搞懂大模型的重复惩罚后处理
- 2024-11-18基于Ollama和pgai的个人知识助手项目:用Postgres和向量扩展打造智能数据库
- 2024-11-15我用同一个提示测试了4款AI工具,看看谁设计的界面更棒
- 2024-11-15深度学习面试的时候,如何回答1x1卷积的作用
- 2024-11-15检索增强生成即服务:开发者的得力新帮手
- 2024-11-15技术与传统:人工智能时代的最后一袭纱丽
- 2024-11-15未结构化数据不仅仅是给嵌入用的:利用隐藏结构提升检索性能
- 2024-11-15Emotion项目实战:新手入门教程
- 2024-11-157 个开源库助你构建增强检索生成(RAG)、代理和 AI 搜索