# Tag Info

3

"Modern" Guarantees for Feed-Forward Neural Networks My answer will complement nbro's above, which gave a very nice overview of universal approximation theorems for different types of commonly used architectures, by focusing on recent developments specifically for feed-forward networks. I'll try an emphasis depth over breadth (sometimes called ...

0

This paper Can Machines Design? An Artificial General Intelligence Approach (2018, presented at AGI-18 and published in the related proceedings here), which proposes the design Gödel machine, may be useful to you. After a quick search, I have not found other relevant papers, so I suppose that the research on GMs is currently not very active.

1

Artificial intelligence is a broad field: that's why Artificial Intelligence: A Modern Approach may look a bit dense to newcomers, given that it covers many different aspects of AI, such as search, machine learning, and natural language processing. The first book in this answer is a good book, but it focuses on evolutionary computation approaches, which are ...

0

I've asked this on rl-list and got lots of interesting references to research papers. So far the most promising one I've seen is this: Nicolas Anastassacos, Stephen Hailes and Mirco Musolesi. Partner Selection for the Emergence of Cooperation in Multi-Agent Systems using Reinforcement Learning. In AAAI 2020. New York City, NY, USA. February 2020.

0

To my knowledge, there does not exist anything along the lines of model-based reinforcement learning with time-sensitive data. I think the best chance you have is to try to abstract the data that you have into a model which is not time-sensitive. What would happen when you get past the timestamps of your original data? I am guessing that when testing this ...

1

Look at spatio-temporal CNNs which extend the image-based CNN in 2D to 3D to handle time. These are commonly used to detect or classify action in a video. People have used them to identify specific actions in various sports such as kicking a soccer ball, throwing a baseball or dribbling a basketball. They have been used to identify fire, smoke, deep fakes,...

1

Today one of the challenges is learning representations/concepts that are causally invariant. Once we have good representations then we can work on the reasoning aspect. There are 2 camps of people today. One believes that symbolic manipulation cannot be achieved properly by deep networks. Hence, they separate the task of extracting a lower-dimensional ...

2

There's not much to derive here it's simply a definition of Bellman operator, it comes from Bellman equation. If you're wondering why $$Q^{\pi} = (I - \gamma P^{\pi})^{-1}r \tag{1}$$ they state that $Q^{\pi}$ is a fixed point which means if you apply Bellman operator to it you get the same value T^{\pi}(Q^{\pi}) = ...

Top 50 recent answers are included