Difference between revisions of "Lifelong Learning"
m |
m (Text replacement - "http:" to "https:") |
||
| Line 5: | Line 5: | ||
|description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools | |description=Helpful resources for your journey with artificial intelligence; videos, articles, techniques, courses, profiles, and tools | ||
}} | }} | ||
| − | [ | + | [https://www.youtube.com/results?search_query=lifelong+learning+neural+network+Multi+model YouTube search...] |
| − | [ | + | [https://www.google.com/search?q=lifelong+learning+neural+network+Multi+model ...Google search] |
* [[Learning Techniques]] | * [[Learning Techniques]] | ||
** [[Reinforcement Learning (RL)]] | ** [[Reinforcement Learning (RL)]] | ||
** [[Transfer Learning]] | ** [[Transfer Learning]] | ||
| − | * [ | + | * [https://www.darpa.mil/program/lifelong-learning-machines Lifelong Learning Machines (L2M) | DARPA] |
| − | * [ | + | * [https://www.darpa.mil/news-events/2019-03-12 Progress on Lifelong Learning Machines Shows Potential for Bio-Inspired Algorithms | USC & DARPA] |
| − | * [ | + | * [https://www.darpa.mil/news-events/2018-05-03 Researchers Selected to Develop Novel Approaches to Lifelong Machine Learning | DARPA] |
* [[Generative AI]] ... [[OpenAI]]'s [[ChatGPT]] ... [[Perplexity]] ... [[Microsoft]]'s [[BingAI]] ... [[You]] ...[[Google]]'s [[Bard]] ... [[Baidu]]'s [[Ernie]] | * [[Generative AI]] ... [[OpenAI]]'s [[ChatGPT]] ... [[Perplexity]] ... [[Microsoft]]'s [[BingAI]] ... [[You]] ...[[Google]]'s [[Bard]] ... [[Baidu]]'s [[Ernie]] | ||
| − | In recent years, researchers have developed deep neural networks that can perform a variety of tasks, including visual recognition and natural language processing (NLP) tasks. Although many of these models achieved remarkable results, they typically only perform well on one particular task due to what is referred to as "catastrophic forgetting." Essentially, catastrophic forgetting means that when a model that was initially trained on task A is later trained on task B, its performance on task A will significantly decline. [ | + | In recent years, researchers have developed deep neural networks that can perform a variety of tasks, including visual recognition and natural language processing (NLP) tasks. Although many of these models achieved remarkable results, they typically only perform well on one particular task due to what is referred to as "catastrophic forgetting." Essentially, catastrophic forgetting means that when a model that was initially trained on task A is later trained on task B, its performance on task A will significantly decline. [https://techxplore.com/news/2019-03-approach-multi-model-deep-neural-networks.html A new approach to overcome multi-model forgetting in deep neural networks] and [https://techxplore.com/news/2019-03-memory-approach-enable-lifelong.html A generative memory approach to enable lifelong reinforcement learning] | Ingrid Fadelli |
| − | + | https://3c1703fe8d.site.internapcdn.net/newman/csz/news/800/2019/11-anewapproach.jpg | |
<youtube>6PlvyWQUQu8</youtube> | <youtube>6PlvyWQUQu8</youtube> | ||
| Line 28: | Line 28: | ||
<youtube>qRXPS_6fAfE</youtube> | <youtube>qRXPS_6fAfE</youtube> | ||
| − | * [ | + | * [https://techxplore.com/news/2018-10-developmental-approach-sensorimotor-space-enlargement.html A new developmental reinforcement learning approach for sensorimotor space enlargement | Ingrid Fadelli] |
| − | + | https://3c1703fe8d.site.internapcdn.net/newman/csz/news/800/2018/4-anewdevelopm.jpg | |
== Forgetting == | == Forgetting == | ||
| − | [ | + | [https://www.youtube.com/results?search_query=Catastrophic+Forgetting+neural+networkMulti+model YouTube search...] |
| − | [ | + | [https://www.google.com/search?q=Catastrophic+Forgetting+neural+network+Multi+model ...Google search] |
| − | In the quest to build AI that goes beyond today's single-purpose machines, scientists are developing new tools to help AI remember the right things — and forget the rest. [ | + | In the quest to build AI that goes beyond today's single-purpose machines, scientists are developing new tools to help AI remember the right things — and forget the rest. [https://www.axios.com/ai-memory-forgetting-336e0525-b4ca-4bec-bed5-745b3d613f65.html Saving AI from catastrophic forgetting | Kaveh Waddell - Axios] |
| − | * [ | + | * [https://www.axios.com/memory-forgetting-neuroscience-brain-ebefed70-2d00-4340-a53d-8b58bbb5d522.html Special report: The future of forgetting | Alison Snyder - Axios] |
| − | * [ | + | * [https://www.quantamagazine.org/to-remember-the-brain-must-actively-forget-20180724/ To Remember, the Brain Must Actively Forget | Toma Vagner - Quanta Magazine] |
| − | * [ | + | * [https://www.nytimes.com/2019/03/22/health/memory-forgetting-psychology.html Can We Get Better at Forgetting? Some things aren’t worth remembering. Science is slowly working out how we might let that stuff go. | Benedict Carey - The New York Times] |
| − | * [ | + | * [https://venturebeat.com/2020/02/25/openais-jeff-clune-on-deep-learnings-achilles-heel-and-a-faster-path-to-agi/ OpenAI’s Jeff Clune on deep learning’s Achilles’ heel and a faster path to artificial general intelligence (AGI) - Khari Johnson - VentureBeat] |
| − | * [ | + | * [https://en.wikipedia.org/wiki/Catastrophic_interference Catastrophic Interference] |
| − | === [ | + | === [https://www.vice.com/en_us/article/evym4m/ai-told-me-human-face-neural-networks Watching AI Slowly Forget a Human Face Is Incredibly Creepy] === |
Revision as of 21:12, 28 March 2023
YouTube search... ...Google search
- Learning Techniques
- Lifelong Learning Machines (L2M) | DARPA
- Progress on Lifelong Learning Machines Shows Potential for Bio-Inspired Algorithms | USC & DARPA
- Researchers Selected to Develop Novel Approaches to Lifelong Machine Learning | DARPA
- Generative AI ... OpenAI's ChatGPT ... Perplexity ... Microsoft's BingAI ... You ...Google's Bard ... Baidu's Ernie
In recent years, researchers have developed deep neural networks that can perform a variety of tasks, including visual recognition and natural language processing (NLP) tasks. Although many of these models achieved remarkable results, they typically only perform well on one particular task due to what is referred to as "catastrophic forgetting." Essentially, catastrophic forgetting means that when a model that was initially trained on task A is later trained on task B, its performance on task A will significantly decline. A new approach to overcome multi-model forgetting in deep neural networks and A generative memory approach to enable lifelong reinforcement learning | Ingrid Fadelli
Forgetting
YouTube search... ...Google search
In the quest to build AI that goes beyond today's single-purpose machines, scientists are developing new tools to help AI remember the right things — and forget the rest. Saving AI from catastrophic forgetting | Kaveh Waddell - Axios
- Special report: The future of forgetting | Alison Snyder - Axios
- To Remember, the Brain Must Actively Forget | Toma Vagner - Quanta Magazine
- Can We Get Better at Forgetting? Some things aren’t worth remembering. Science is slowly working out how we might let that stuff go. | Benedict Carey - The New York Times
- OpenAI’s Jeff Clune on deep learning’s Achilles’ heel and a faster path to artificial general intelligence (AGI) - Khari Johnson - VentureBeat
- Catastrophic Interference
Watching AI Slowly Forget a Human Face Is Incredibly Creepy
