Difference between revisions of "Lifelong Learning"
Line 11: | Line 11: | ||
* [http://www.darpa.mil/news-events/2019-03-12 Progress on Lifelong Learning Machines Shows Potential for Bio-Inspired Algorithms | USC & DARPA] | * [http://www.darpa.mil/news-events/2019-03-12 Progress on Lifelong Learning Machines Shows Potential for Bio-Inspired Algorithms | USC & DARPA] | ||
* [http://www.darpa.mil/news-events/2018-05-03 Researchers Selected to Develop Novel Approaches to Lifelong Machine Learning | DARPA] | * [http://www.darpa.mil/news-events/2018-05-03 Researchers Selected to Develop Novel Approaches to Lifelong Machine Learning | DARPA] | ||
− | * [[Reinforcement Learning (RL)]] | + | * [[Learning Techniques]] |
− | * [[Transfer Learning]] | + | ** [[Reinforcement Learning (RL)]] |
+ | ** [[Transfer Learning]] | ||
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. [http://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 | 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. [http://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 |
Revision as of 15:21, 8 December 2019
YouTube search... ...Google search
- 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
- Learning Techniques
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
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
Watching AI Slowly Forget a Human Face Is Incredibly Creepy