Butterflies, only 32 grams each, including two servos, a pair of small batteries, & a laser-made casing. Soon these butterflies achieve superbutterfly intelligence, control the world's nectar supply, & tile the universe with their eggs. https://www.festo.com/group/en/cms/10216.htm
https://twitter.com/Reza_Zadeh/status/1077294105137360896
#machinelearning
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
https://twitter.com/Reza_Zadeh/status/1077294105137360896
#machinelearning
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
A structural transition in physical networks
https://www.nature.com/articles/s41586-018-0726-6
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
https://www.nature.com/articles/s41586-018-0726-6
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
Deep learning made easier with transfer learning http://bit.ly/2PZD7et #AI #DeepLearning #MachineLearning #DataScience
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
A deep thread that's worth a read by anyone interested in #deeplearning. (And we just launched a Deep Learning Fundamentals course, by the way: http://bit.ly/2SXnrtT )
Explain More:
Regulations, arguably, should not be based on detailed understanding of how AI systems work (which the regulators can't have in any depth). However, AI systems need to be able to explain decisions in terms that humans can understand, if we are to consider them trustworthy. Not explanations involving specifics of the algorithms, weights in a neural network, etc., but explanations that engage people's theories of mind, explanations at the level of Dennett's intentional stance - in terms of values, goals, plans, and intentions.
Previous computer systems, to be comprehensible, and, yes, trustworthy, needed to consistently present behavior that fit people's natural inferences to physical models (e.g., the "desktop"). Anyone old enough to remember programming VCRs? Nerdview is a failure of explanation.
AI systems will need to engage not the mind's physics inference, but its *social* inference (theory of mind). AI systems should behave as minds, and explain their behavior as minds. They must have failure modes predictable and comprehensible like human ones (or physical ones).
The counterargument of "How does a system explain how it decided that a stop sign was there? By listing network weights in a perceptual model?!" is a crimson herring. If the perceptual system is accurate enough in human terms (i.e., without crazy error modes), it can just say "I saw a stop sign," just like a human would. Full stop. More complex decisions, like swerving to avoid a bicyclist and then hitting a pedestrian would require more complex explanations involving values, goals, and intentions, as well as perception ("I didn't see the guy").
Saying that we attain trustworthiness of AI systems just based on experimental performance metrics, however rigorous and comprehensive, is utterly misguided. Measurable performance is necessary, but not at all sufficient, for (at least) two reasons.
First, it is virtually impossible, for a non-specialist to evaluate the sufficiency of an experimental methodology or significance of the results. It's very easy to create misleading experiments, even without intending to. So this can only create trust among the credulous.
Second, experimental performance guarantees do nothing to develop trust between an AI system and the humans it interacts with - that trust must develop through the interaction, which must therefore be comprehensible and explainable.
In a word, to attain trustworthiness, AI systems must be able to form *relationships* with people. Not necessarily deep relationships, but still they must engage with the human mind's systems of social connection.
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
Explain More:
Regulations, arguably, should not be based on detailed understanding of how AI systems work (which the regulators can't have in any depth). However, AI systems need to be able to explain decisions in terms that humans can understand, if we are to consider them trustworthy. Not explanations involving specifics of the algorithms, weights in a neural network, etc., but explanations that engage people's theories of mind, explanations at the level of Dennett's intentional stance - in terms of values, goals, plans, and intentions.
Previous computer systems, to be comprehensible, and, yes, trustworthy, needed to consistently present behavior that fit people's natural inferences to physical models (e.g., the "desktop"). Anyone old enough to remember programming VCRs? Nerdview is a failure of explanation.
AI systems will need to engage not the mind's physics inference, but its *social* inference (theory of mind). AI systems should behave as minds, and explain their behavior as minds. They must have failure modes predictable and comprehensible like human ones (or physical ones).
The counterargument of "How does a system explain how it decided that a stop sign was there? By listing network weights in a perceptual model?!" is a crimson herring. If the perceptual system is accurate enough in human terms (i.e., without crazy error modes), it can just say "I saw a stop sign," just like a human would. Full stop. More complex decisions, like swerving to avoid a bicyclist and then hitting a pedestrian would require more complex explanations involving values, goals, and intentions, as well as perception ("I didn't see the guy").
Saying that we attain trustworthiness of AI systems just based on experimental performance metrics, however rigorous and comprehensive, is utterly misguided. Measurable performance is necessary, but not at all sufficient, for (at least) two reasons.
First, it is virtually impossible, for a non-specialist to evaluate the sufficiency of an experimental methodology or significance of the results. It's very easy to create misleading experiments, even without intending to. So this can only create trust among the credulous.
Second, experimental performance guarantees do nothing to develop trust between an AI system and the humans it interacts with - that trust must develop through the interaction, which must therefore be comprehensible and explainable.
In a word, to attain trustworthiness, AI systems must be able to form *relationships* with people. Not necessarily deep relationships, but still they must engage with the human mind's systems of social connection.
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
Kaggle kernels that Researcher have published.
1. Time Series Analysis - Artificial Neural Networks - https://lnkd.in/f8diQkX
2. Titanic - Data Preprocessing and Visualization - https://lnkd.in/fwrvHr5
3. Everything you can do with Seaborn - https://lnkd.in/fpgQCr8
4. Insights of Kaggle ML and DS Survey - https://lnkd.in/fPyiGyU
5. Time Series Analysis - ARIMA model - https://lnkd.in/fn24ihz
6. Time Series Analysis - LSTM - https://lnkd.in/fuY6DXm
7. Introduction to Regression - Complete Analysis - https://lnkd.in/fM3xsZ2
8. Time Series - Preprocessing to Modelling - https://lnkd.in/fJcar4u
Kaggle community is one of the best community for Data Science.
#machinelearning #artificialintelligence #datascience #deeplearning #data
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
1. Time Series Analysis - Artificial Neural Networks - https://lnkd.in/f8diQkX
2. Titanic - Data Preprocessing and Visualization - https://lnkd.in/fwrvHr5
3. Everything you can do with Seaborn - https://lnkd.in/fpgQCr8
4. Insights of Kaggle ML and DS Survey - https://lnkd.in/fPyiGyU
5. Time Series Analysis - ARIMA model - https://lnkd.in/fn24ihz
6. Time Series Analysis - LSTM - https://lnkd.in/fuY6DXm
7. Introduction to Regression - Complete Analysis - https://lnkd.in/fM3xsZ2
8. Time Series - Preprocessing to Modelling - https://lnkd.in/fJcar4u
Kaggle community is one of the best community for Data Science.
#machinelearning #artificialintelligence #datascience #deeplearning #data
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
Machine Theory of Mind
Paper by Rabinowitz et al.: https://lnkd.in/eQY6C9N
#artificialintelligence #machinelearning #reinforcementlearning
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
Paper by Rabinowitz et al.: https://lnkd.in/eQY6C9N
#artificialintelligence #machinelearning #reinforcementlearning
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
Automatic Poetry Generation with Mutual Reinforcement Learning"
By Xiaoyuan Yi, Maosong Sun, Ruoyu Li and Wenhao Li: https://lnkd.in/e4nUi9B
#ArtificialIntelligence #DeepLearning #MachineLearning #ReinforcementLearning
❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN
By Xiaoyuan Yi, Maosong Sun, Ruoyu Li and Wenhao Li: https://lnkd.in/e4nUi9B
#ArtificialIntelligence #DeepLearning #MachineLearning #ReinforcementLearning
❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN
Artificial Intelligence Index 2018
https://lnkd.in/dBNzrca
#artificialintelligence
❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN
https://lnkd.in/dBNzrca
#artificialintelligence
❇️ @AI_Python
🗣 @AI_Python_Arxiv
✴️ @AI_Python_EN
"Playing a game of GANstruction"
Blog by Helena Sarin: https://lnkd.in/dZ6T4tc
#ArtificialIntelligence #DeepLearning #GenerativeAdversarialNetworks #MachineLearning
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
Blog by Helena Sarin: https://lnkd.in/dZ6T4tc
#ArtificialIntelligence #DeepLearning #GenerativeAdversarialNetworks #MachineLearning
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
If you are ready to step up your artificial intelligence skills to a new level, Reinforcement Learning is the next step (after Machine Learning and Deep Learning). Here is a good book on Reinforcement Learning.
Reinforcement Learning: An Introduction
Book by Andrew Barto and Richard S. Sutton
Download: https://lnkd.in/eV42FUP
#reinforcementlearning #machinelearning #artificialintelligence #ai #datascience
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
Reinforcement Learning: An Introduction
Book by Andrew Barto and Richard S. Sutton
Download: https://lnkd.in/eV42FUP
#reinforcementlearning #machinelearning #artificialintelligence #ai #datascience
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
Python Plotting With Matplotlib (Guide) – Real Python http://bit.ly/2QKqQzw
#AI #DeepLearning #MachineLearning #DataScience
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
#AI #DeepLearning #MachineLearning #DataScience
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
Reza Zadeh:
Creating super slow motion videos by predicting missing frames using a neural network, instead of simple interpolation. With code.
Code: https://github.com/avinashpaliwal/Super-SloMo
Project: https://people.cs.umass.edu/~hzjiang/projects/superslomo/
#AI #DeepLearning #MachineLearning #DataScience #neuralnetwork
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
Creating super slow motion videos by predicting missing frames using a neural network, instead of simple interpolation. With code.
Code: https://github.com/avinashpaliwal/Super-SloMo
Project: https://people.cs.umass.edu/~hzjiang/projects/superslomo/
#AI #DeepLearning #MachineLearning #DataScience #neuralnetwork
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
t's interesting that we expect #ML algorithms to explain themselves when humans can't even do that. Maybe the task is to observe enough AI decisions to make them an object of study - that is, to try to back out patterns and give them meaning. A psychology of machines if you will.
AlphaZero taught itself the principles of chess, and In a matter of hours became the best player the world has ever seen.
https://t.co/Cc6eZXo0q7
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
AlphaZero taught itself the principles of chess, and In a matter of hours became the best player the world has ever seen.
https://t.co/Cc6eZXo0q7
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
Hunt for talented #machinelearning engineers and professionals was already intensifying in 2015 onwards.
Will hunt for #deeplearning engineers create even bigger waves in the #AI economy?
"How Machine Learning Is Transforming The Hunt for Talent – Part Deux" which he writes occasionally on his personal website.
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
Will hunt for #deeplearning engineers create even bigger waves in the #AI economy?
"How Machine Learning Is Transforming The Hunt for Talent – Part Deux" which he writes occasionally on his personal website.
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
The Eye In The Sky"
Satellite Image Classification using Semantic Segmentation
By Manideep Kolla, Apoorva Kumar, Aniket Mandle
GitHub repository: https://lnkd.in/eB2g-dX
#artificialintelligence #deeplearning #machinelearning #keras #tensorflow
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
Satellite Image Classification using Semantic Segmentation
By Manideep Kolla, Apoorva Kumar, Aniket Mandle
GitHub repository: https://lnkd.in/eB2g-dX
#artificialintelligence #deeplearning #machinelearning #keras #tensorflow
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
What is required today is not Artificial but Collaborative intelligence. Humans and AI can co-exist for a better and a promising tomorrow.
#ai
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python
#ai
✴️ @AI_Python_EN
🗣 @AI_Python_arXiv
❇️ @AI_Python