<div style="text-align:center"><img src="https://user-images.githubusercontent.com/8284677/74609985-02087e80-50e7-11ea-9562-218dec34714d.png" height="250"></div>
Implementation of a Non-Axiomatic Reasoning System [6], a general-purpose reasoner that adapts under the Assumption of Insufficient Knowledge and Resources [7].
This is a completely new platform and not branched from the existing OpenNARS codebase. The ONA (OpenNARS for Applications) system [1] takes the logic and conceptual ideas of OpenNARS, the event handling and procedure learning capabilities of ANSNA [2, 3], and the control model from ALANN [4]. The system is written in C, is more capable than our previous implementations, and has also been experimentally compared with Reinforcement Learning [5].
The ONA implementation has been developed with a pragmatic mindset. The focus on the design has been to implement the 'existing' theory [6, 7] as effectively as possible and make firm decisions rather than keep as many options open as possible. This has led to some small conceptual differences to OpenNARS [8] which was developed for research purposes.
Video tutorials and demo videos can be found here: [Video tutorials](https://github.com/opennars/OpenNARS-for-Applications/wiki/Video-tutorials)
***How to clone and compile (tested with GCC and Clang for x64, x86 and ARM):***
```
git clone https://github.com/opennars/OpenNARS-for-Applications
cd OpenNARS-for-Applications
./build.sh
```
***How to set the amount of threads the system should run with: (to be tested more, compile with ./build.sh -fopenmp)***
```
export OMP_NUM_THREADS=4 // 4 threads seems to be the sweet spot. More threads leads to more contention and less speed currently
```
***How to run the interactive Narsese shell:***
```
./NAR shell
```
***with syntax highlighting:***
```
./NAR shell | python3 colorize.py
```
***with English NLP shell and syntax highlighting:***
```
python3 english_to_narsese.py | ./NAR shell | python3 colorize.py
```
***How to run the C tests and then receive instructions how to run the current example programs:***
```
./NAR
```
***How to run all C tests, and all Narsese and English examples as integration tests, and collect metrics across all examples:***
```
python3 evaluation.py
```
For the current output, see [Evaluation results](https://github.com/opennars/OpenNARS-for-Applications/wiki/Evaluation-Results-(Tests,-metrics))
**How to run an example file:**
Narsese:
```
./NAR shell < ./examples/nal/example1.nal
```
English: (tested with NLTK v3.4.5, v3.5)
```
python3 english_to_narsese.py < ./examples/english/story1.english | ./NAR shell
```
**How to run an UDPNAR:**
```
./NAR UDPNAR IP PORT timestep(ns per cycle) printDerivations
./NAR UDPNAR 127.0.0.1 50000 10000000 true
```
where the output can be logged simply by appending
```
> output.log
```
**How to reach us:**
Real-time team chat: #nars IRC channel @ freenode.net, #nars:matrix.org (accessible via Riot.im)
Google discussion group: https://groups.google.com/forum/#!forum/open-nars
**References**
[1] Hammer, P., & Lofthouse, T. (2020, September). ‘OpenNARS for Applications’: Architecture and Control. In International Conference on Artificial General Intelligence (pp. 193-204). Springer, Cham.
[2] Hammer, P. (2019, August). Adaptive Neuro-Symbolic Network Agent. In International Conference on Artificial General Intelligence (pp. 80-90). Springer, Cham.
[3] Hammer, P., & Lofthouse, T. (2018, August). Goal-directed procedure learning. In International Conference on Artificial General Intelligence (pp. 77-86). Springer, Cham.
[4] Lofthouse, T. (2019). ALANN: An event driven control mechanism for a non-axiomatic reasoning system (NARS).
[5] Eberding, L. M., Thórisson, K. R., Sheikhlar, A., & Andrason, S. P. (2020). SAGE: Task-Environment Platform for Evaluating a Broad Range of AI Learners. In Artificial General Intelligence: 13th International Conference, AGI 2020, St. Petersburg, Russia, September 16–19, 2020, Proceedings (Vol. 12177, p. 72). Springer Nature.
[6] Wang, P. (2013). Non-axiomatic logic: A model of intelligent reasoning. World Scientific.
[7] Wang, P. (2009, October). Insufficient Knowledge and Resources-A Biological Constraint and Its Functional Implications. In AAAI Fall Symposium: Biologically Inspired Cognitive Architectures.
[8] Hammer, P., Lofthouse, T., & Wang, P. (2016, July). The OpenNARS implementation of the non-axiomatic reasoning system. In International conference on artificial general intelligence (pp. 160-170). Springer, Cham.
没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
收起资源包目录
【通用人工智能】基于java开发的人工智能推理系统 (136个子文件)
Cycle.c 28KB
Narsese.c 23KB
Memory.c 19KB
Decision.c 15KB
Shell.c 11KB
Inference.c 9KB
Variable.c 9KB
NAR.c 8KB
NAL.c 7KB
PriorityQueue.c 7KB
Truth.c 6KB
InvertedAtomIndex.c 5KB
main.c 5KB
HashTable.c 5KB
Table.c 4KB
UDPNAR.c 4KB
Stats.c 3KB
Term.c 3KB
Stamp.c 3KB
FIFO.c 3KB
UDP.c 2KB
Globals.c 2KB
Metric.c 2KB
Stack.c 2KB
Usage.c 2KB
Event.c 2KB
main.c 441B
ona.cpp 4KB
ona-ros_node.cpp 2KB
main.cpp 647B
grammar.english 1KB
dialog.english 1KB
robotQA.english 1KB
story4.english 652B
disambiguate.english 574B
babi1.english 446B
story2.english 422B
story1.english 409B
story3.english 371B
.gitignore 41B
Robot_Test.h 16KB
Testchamber_Test.h 14KB
NAL.h 7KB
Pong2_Test.h 5KB
HashTable_Test.h 5KB
Config.h 5KB
InvertedAtomIndex_Test.h 4KB
Pong_Test.h 4KB
Sequence_Test.h 4KB
Memory.h 4KB
Narsese.h 3KB
Alien_Test.h 3KB
Follow_Test.h 3KB
Cartpole_Test.h 3KB
Truth.h 3KB
Multistep_Test.h 3KB
PriorityQueue.h 3KB
Inference.h 3KB
FIFO_Test.h 3KB
Multistep2_Test.h 3KB
Variable.h 3KB
Table_Test.h 2KB
HashTable.h 2KB
Globals.h 2KB
Stack_Test.h 2KB
InvertedAtomIndex.h 2KB
PriorityQueue_Test.h 2KB
Term.h 2KB
Decision.h 2KB
Memory_Test.h 2KB
UDPNAR_Test.h 2KB
UDP_Test.h 2KB
NAR.h 2KB
Procedure_Test.h 2KB
Table.h 2KB
FIFO.h 2KB
Narsese_Test.h 2KB
UDP.h 2KB
Event.h 2KB
Implication.h 2KB
Usage.h 2KB
Stamp.h 2KB
Stack.h 2KB
Shell.h 2KB
Concept.h 2KB
RuleTable.h 2KB
unit_tests.h 2KB
system_tests.h 2KB
Cycle.h 2KB
UDPNAR.h 2KB
Alphabet_Test.h 2KB
Metric.h 2KB
Stats.h 2KB
Stamp_Test.h 2KB
RuleTable_Test.h 1KB
ona.hpp 2KB
LICENSE 1KB
README.md 4KB
CODE_OF_CONDUCT.md 3KB
README.md 602B
共 136 条
- 1
- 2
资源评论
数字孪生小砖家
- 粉丝: 16
- 资源: 7
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功