Twenty Significant Problems in AI Research, with Potential Solutions via the SP Theory of Intelligence and Its Realisation in the SP Computer Model
This paper highlights 20 significant problems in AI research, with potential solutions via the <i>SP Theory of Intelligence</i> (SPTI) and its realisation in the <i>SP Computer Model</i>. With other evidence referenced in the paper, <i>this is strong evidence in support...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Foundations |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-9321/2/4/70 |
| _version_ | 1797624531304579072 |
|---|---|
| author | J. Gerard Wolff |
| author_facet | J. Gerard Wolff |
| author_sort | J. Gerard Wolff |
| collection | DOAJ |
| description | This paper highlights 20 significant problems in AI research, with potential solutions via the <i>SP Theory of Intelligence</i> (SPTI) and its realisation in the <i>SP Computer Model</i>. With other evidence referenced in the paper, <i>this is strong evidence in support of the SPTI as a promising foundation for the development of human-level broad AI, aka artificial general intelligence</i>. The 20 problems include: the tendency of deep neural networks to make major errors in recognition; the need for a coherent account of generalisation, over- and under-generalisation, and minimising the corrupting effect of ‘dirty data’; how to achieve one-trial learning; how to achieve transfer learning; the need for transparency in the representation and processing of knowledge; and how to eliminate the problem of catastrophic forgetting. In addition to its promise as a foundation for the development of AGI, the SPTI has potential as a foundation for the study of human learning, perception, and cognition. And it has potential as a foundation for mathematics, logic, and computing. |
| first_indexed | 2024-03-11T09:43:38Z |
| format | Article |
| id | doaj.art-38cdb6e4f65c43e4ad84a72ef173a547 |
| institution | Directory Open Access Journal |
| issn | 2673-9321 |
| language | English |
| last_indexed | 2024-03-11T09:43:38Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Foundations |
| spelling | doaj.art-38cdb6e4f65c43e4ad84a72ef173a5472023-11-16T16:43:02ZengMDPI AGFoundations2673-93212022-11-01241045107910.3390/foundations2040070Twenty Significant Problems in AI Research, with Potential Solutions via the SP Theory of Intelligence and Its Realisation in the SP Computer ModelJ. Gerard Wolff0CognitionResearch.org, 18 Penlon, Menai Bridge, Anglesey LL59 5LR, UKThis paper highlights 20 significant problems in AI research, with potential solutions via the <i>SP Theory of Intelligence</i> (SPTI) and its realisation in the <i>SP Computer Model</i>. With other evidence referenced in the paper, <i>this is strong evidence in support of the SPTI as a promising foundation for the development of human-level broad AI, aka artificial general intelligence</i>. The 20 problems include: the tendency of deep neural networks to make major errors in recognition; the need for a coherent account of generalisation, over- and under-generalisation, and minimising the corrupting effect of ‘dirty data’; how to achieve one-trial learning; how to achieve transfer learning; the need for transparency in the representation and processing of knowledge; and how to eliminate the problem of catastrophic forgetting. In addition to its promise as a foundation for the development of AGI, the SPTI has potential as a foundation for the study of human learning, perception, and cognition. And it has potential as a foundation for mathematics, logic, and computing.https://www.mdpi.com/2673-9321/2/4/70artificial intelligenceSP Theory of Intelligenceinformation compressiondeep neural networks |
| spellingShingle | J. Gerard Wolff Twenty Significant Problems in AI Research, with Potential Solutions via the SP Theory of Intelligence and Its Realisation in the SP Computer Model Foundations artificial intelligence SP Theory of Intelligence information compression deep neural networks |
| title | Twenty Significant Problems in AI Research, with Potential Solutions via the SP Theory of Intelligence and Its Realisation in the SP Computer Model |
| title_full | Twenty Significant Problems in AI Research, with Potential Solutions via the SP Theory of Intelligence and Its Realisation in the SP Computer Model |
| title_fullStr | Twenty Significant Problems in AI Research, with Potential Solutions via the SP Theory of Intelligence and Its Realisation in the SP Computer Model |
| title_full_unstemmed | Twenty Significant Problems in AI Research, with Potential Solutions via the SP Theory of Intelligence and Its Realisation in the SP Computer Model |
| title_short | Twenty Significant Problems in AI Research, with Potential Solutions via the SP Theory of Intelligence and Its Realisation in the SP Computer Model |
| title_sort | twenty significant problems in ai research with potential solutions via the sp theory of intelligence and its realisation in the sp computer model |
| topic | artificial intelligence SP Theory of Intelligence information compression deep neural networks |
| url | https://www.mdpi.com/2673-9321/2/4/70 |
| work_keys_str_mv | AT jgerardwolff twentysignificantproblemsinairesearchwithpotentialsolutionsviathesptheoryofintelligenceanditsrealisationinthespcomputermodel |