Insights on Sensorimotor Object Modeling from “Animate Vision” by Dana Ballard - 27 September, 2021
Marcus Lewis reviews a few papers from Dana Ballard and highlights some insights related to object modeling and reference frames in the Thousand Brains Theory.
Marcus first gives an overview of what “animate vision” is, as outlined in Ballard’s papers, and defines optic flow. Marcus then makes a case for using a world-centric, viewer-oriented location relative to a fixation point to represent objects and depth.
In the second part of his presentation, he looks at Numenta’s previous sensorimotor research (where the motor command is being received by the system) and Ballard’s sensorimotor “animate vision” system (where the motor command is being generated by the system) for objecting modeling. He evaluates whether the two sensorimotor frameworks will lead to different object modeling solutions and discusses the opportunities that could stem from Ballard’s framework.
Papers by Dana Ballard:
➤ “Animate Vision” (1990): https://www.sciencedirect.com/science/article/abs/pii/0004370291900804
➤ “Eye Fixation and Early Vision: Kinetic Depth” (1988): https://ieeexplore.ieee.org/document/590033
➤ “Reference Frames for Animate Vision” (1989): https://www.ijcai.org/Proceedings/89-2/Papers/124.pdf
➤ “Principles of Animate Vision” (1992): https://www.sciencedirect.com/science/article/abs/pii/104996609290081D
➤ “Deictic Codes for the Embodiment of Cognition” (1997): https://www.cs.utexas.edu/~dana/bbs.pdf
Papers by Numenta:
➤ “Locations in the Neocortex: A Theory of Sensorimotor Object Recognition Using Cortical Grid Cells”: https://www.frontiersin.org/articles/10.3389/fncir.2019.00022/full
➤ “A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex”: https://www.frontiersin.org/articles/10.3389/fncir.2018.00121/full
- - - - -
Numenta is leading the new era of machine intelligence. Our deep experience in theoretical neuroscience research has led to tremendous discoveries on how the brain works. We have developed a framework called the Thousand Brains Theory of Intelligence that will be fundamental to advancing the state of artificial intelligence and machine learning. By applying this theory to existing deep learning systems, we are addressing today’s bottlenecks while enabling tomorrow’s applications.
Subscribe to our News Digest for the latest news about neuroscience and artificial intelligence:
https://numenta.com/news-digest/
Subscribe to our Newsletter for the latest Numenta updates:
https://tinyurl.com/NumentaNewsletter
Our Social Media:
https://twitter.com/Numenta
https://www.facebook.com/OfficialNumenta
https://www.linkedin.com/company/numenta
Our Open Source Resources:
https://github.com/numenta
https://discourse.numenta.org/
Our Website:
https://numenta.com/
Видео Insights on Sensorimotor Object Modeling from “Animate Vision” by Dana Ballard - 27 September, 2021 канала Numenta
Marcus first gives an overview of what “animate vision” is, as outlined in Ballard’s papers, and defines optic flow. Marcus then makes a case for using a world-centric, viewer-oriented location relative to a fixation point to represent objects and depth.
In the second part of his presentation, he looks at Numenta’s previous sensorimotor research (where the motor command is being received by the system) and Ballard’s sensorimotor “animate vision” system (where the motor command is being generated by the system) for objecting modeling. He evaluates whether the two sensorimotor frameworks will lead to different object modeling solutions and discusses the opportunities that could stem from Ballard’s framework.
Papers by Dana Ballard:
➤ “Animate Vision” (1990): https://www.sciencedirect.com/science/article/abs/pii/0004370291900804
➤ “Eye Fixation and Early Vision: Kinetic Depth” (1988): https://ieeexplore.ieee.org/document/590033
➤ “Reference Frames for Animate Vision” (1989): https://www.ijcai.org/Proceedings/89-2/Papers/124.pdf
➤ “Principles of Animate Vision” (1992): https://www.sciencedirect.com/science/article/abs/pii/104996609290081D
➤ “Deictic Codes for the Embodiment of Cognition” (1997): https://www.cs.utexas.edu/~dana/bbs.pdf
Papers by Numenta:
➤ “Locations in the Neocortex: A Theory of Sensorimotor Object Recognition Using Cortical Grid Cells”: https://www.frontiersin.org/articles/10.3389/fncir.2019.00022/full
➤ “A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex”: https://www.frontiersin.org/articles/10.3389/fncir.2018.00121/full
- - - - -
Numenta is leading the new era of machine intelligence. Our deep experience in theoretical neuroscience research has led to tremendous discoveries on how the brain works. We have developed a framework called the Thousand Brains Theory of Intelligence that will be fundamental to advancing the state of artificial intelligence and machine learning. By applying this theory to existing deep learning systems, we are addressing today’s bottlenecks while enabling tomorrow’s applications.
Subscribe to our News Digest for the latest news about neuroscience and artificial intelligence:
https://numenta.com/news-digest/
Subscribe to our Newsletter for the latest Numenta updates:
https://tinyurl.com/NumentaNewsletter
Our Social Media:
https://twitter.com/Numenta
https://www.facebook.com/OfficialNumenta
https://www.linkedin.com/company/numenta
Our Open Source Resources:
https://github.com/numenta
https://discourse.numenta.org/
Our Website:
https://numenta.com/
Видео Insights on Sensorimotor Object Modeling from “Animate Vision” by Dana Ballard - 27 September, 2021 канала Numenta
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
!["Complementary Learning Systems Theory Updated" Paper Review | Jeff Hawkins | Research | Numenta](https://i.ytimg.com/vi/SIFWscdP7zU/default.jpg)
![The Thousand Brains Theory of Intelligence | Jeff Hawkins | Numenta](https://i.ytimg.com/vi/VqDVUWgJQPI/default.jpg)
![A Zoom Conversation with Numenta CEO Subutai Ahmad](https://i.ytimg.com/vi/_L1RBJmSBHk/default.jpg)
![Plasticity and Learning Algorithms in Models of the Single Neuron - August 25, 2022](https://i.ytimg.com/vi/KLmk3xnojKU/default.jpg)
![Task-Agnostic Continual Reinforcement Learning: In Praise of a Simple Baseline - June 10, 2022](https://i.ytimg.com/vi/dR93mmjNdpc/default.jpg)
![Brains@Bay Meetup - Exploring Neuromodulators and How They Might Impact AI (Apr 13, 2022)](https://i.ytimg.com/vi/4Sgec7yfSiA/default.jpg)
![Tutorial and Discussion on Cortical Column Voting Mechanisms Developed by Numenta - 5 April, 2022](https://i.ytimg.com/vi/QQ0k6Vg8wto/default.jpg)
![How the Brain Works: The Thousand Brains Theory of Intelligence | Numenta](https://i.ytimg.com/vi/LaAYuygr7_8/default.jpg)
![Sparsely-Gated Mixture-of-Experts Paper Review - 18 March, 2022](https://i.ytimg.com/vi/yqJQwLa6Dbg/default.jpg)
![Papers on Equivariant Neural Networks for Object Representation - 11 February, 2022](https://i.ytimg.com/vi/enEuXwKgSVc/default.jpg)
!["Learning Physical Graph Representations from Visual Scenes" Paper Review - December 22, 2021](https://i.ytimg.com/vi/KElvHDn7Mpw/default.jpg)
![Brains@Bay Meetup - Sensorimotor Learning in AI (Dec 15, 2021)](https://i.ytimg.com/vi/YV-wBjel-9s/default.jpg)
![An Overview of Plasticity Mechanisms in the Brain (Part Two) - 15 November, 2021](https://i.ytimg.com/vi/rLpb3J4AHXE/default.jpg)
![An Overview of Plasticity Mechanisms in the Brain (Part One) - 10 November, 2021](https://i.ytimg.com/vi/gbzMt4-3YhY/default.jpg)
![Neural Computation with Dendritic Plateau Potentials - 18 October, 2021](https://i.ytimg.com/vi/hh0TCE790h8/default.jpg)
![Jeff Hawkins at MIT Technology Review's EmTech Conference 2021: Building a Better AI](https://i.ytimg.com/vi/ZrpUoHyKpO8/default.jpg)
![Discussion on Knowledge Transfer Among Cortical Columns - September 29, 2021](https://i.ytimg.com/vi/xuF5Ks6OveU/default.jpg)
![Cortical Column Networks: Learning object identity and pose representations from pixel observations](https://i.ytimg.com/vi/cY2VOVY4u2s/default.jpg)
![Jeff Hawkins on Object Modeling in the Thousand Brains Theory (Part Two) - September 9, 2021](https://i.ytimg.com/vi/HAYxeHWwbNs/default.jpg)
![Jeff Hawkins on Object Modeling in the Thousand Brains Theory (Part One) - September 3, 2021](https://i.ytimg.com/vi/p_KRsF-ncJQ/default.jpg)