ArtificialIntelligenceArticles
2.96K subscribers
1.64K photos
9 videos
5 files
3.86K links
for who have a passion for -
1. #ArtificialIntelligence
2. Machine Learning
3. Deep Learning
4. #DataScience
5. #Neuroscience

6. #ResearchPapers

7. Related Courses and Ebooks
Download Telegram
It’s hard to think of a better place than #Vancouver for #CVPR 2023. Announcing our bid -- a strong organizing team at a beautiful convention centre in a great city.

Greg Mori, Fei-Fei Li, Michael Brown, Yoichi Sato as General Chairs; Vladlen Koltun, Svetlana Lazebnik, Ross Girshick, Andreas Geiger as Program Chairs; Olga Russakovsky and Serena Yeung as Workshop Chairs, Jianxin Wu and Siyu Tang as Tutorial Chairs, Kwang Moo Yi and Leonid Sigal as Local Arrangements Chairs, Catherine Qi Zhao as Doctoral Consortium Chair, Gim Hee Lee and Jon Barron as Demo Chairs.

Check out the full bid document:
www2.cs.sfu.ca/~mori/cvpr2023_vancouver.pdf
"The Bitter Lesson"
The biggest lesson that can be read from 70 years of AI research is that general methods that leverage computation are ultimately the most effective, and by a large margin.
In computer chess, the methods that defeated the world champion, Kasparov, in 1997, were based on massive, deep search (…) A similar pattern of research progress was seen in computer Go, only delayed by a further 20 years.
One thing that should be learned from the bitter lesson is the great power of general purpose methods, of methods that continue to scale with increased computation, even as the available computation becomes very great. The two methods that seem to scale arbitrarily in this way are search and learning.
Rich Sutton, March 13, 2019: https://www.incompleteideas.net/IncIdeas/BitterLesson.html
#Learning #ReinforcementLearning #Search
“AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence”

This paper describes an exciting path that ultimately may be successful at producing general AI. It is based on the clear trend in machine learning that hand-designed solutions eventually are replaced by more effective, learned solutions.

The idea is to create an AI-generating algorithm (AI-GA), which automatically learns how to produce general AI. Three Pillars are essential for the approach: (1) meta-learning architectures, (2) meta-learning the learning algorithms themselves, and (3) generating effective learning environments.

Jeff Clune: https://arxiv.org/abs/1905.10985

#AGI #AGIFirst #ArtificialGeneralIntelligence
A "worrying analysis":

"18 [#deeplearning] algorithms ... presented at top-level research conferences ... Only 7 of them could be reproduced w/ reasonable effort ... 6 of them can often be outperformed w/ comparably simple heuristic methods."
https://arxiv.org/abs/1907.06902v1
One-stage Shape Instantiation from a Single 2D Image to 3D Point Cloud. arxiv.org/abs/1907.10763
Visual Interaction with Deep Learning Models through Collaborative Semantic Inference. arxiv.org/abs/1907.10739