5 votes

Why is the status of artificial life software so under-developed?

I don’t know for certain, but I can make a guess. This is just my opinion, some others may disagree. The field of ALife has four branches that I’m aware of: Self-Organizing/self assembly behavior. ...
user avatar
  • 259
3 votes

How much C++ is needed for research in machine learning and artificial intelligence?

Of course, whether or not you will need to know and use C++ depends on the topics you will research during your Ph.D. or job. If you'll need just to use and/or combine some existing ML models (yes, in ...
user avatar
  • 33.8k
3 votes

Are there any animation tools available to visualise and simulate deep neural networks?

I suggest you take a look at Chris Olah's blog. Has several interesting post including ones on visualizing weights and interpretability. Most of his papers also have Google Colab links so you can ...
user avatar
  • 870
2 votes

How much C++ is needed for research in machine learning and artificial intelligence?

In my experience, knowledge of any particular programming language does not matter. What matters is that you can quickly pick up the basics of a given language. In my professional work I have been ...
user avatar
  • 5,062
2 votes

How can I implement a GAN network for text (review) generation?

As @Clement mentions, text_gen_description gives a good overview!, but the paper seqGAN paper describes the REINFORCE approach more in depth, as they are the first to do it (i believe). This is ...
user avatar
  • 2,249
2 votes
Accepted

Is there any opensource 2d open-world simulation with python API?

You could try Mesa. It has various examples that are commonly-used in agent-based modelling, like Epstein's model, a wolf/sheep predator/prey model, and many more. There is also an introductory ...
user avatar
  • 9,379
2 votes
Accepted

How to evaluate a Deep Q-Network

Q-values represent expected return after taking action $a$ in state $s$, so they do tell you how good it is to take an action in the specific state. Better actions will have larger Q-values. Q-values ...
user avatar
  • 2,226
1 vote
Accepted

Building 'evaluation' neural networks for go, reversi, checkers etc, how to train?

The evaluation of the last steps in the game can be made with the 1 and 0 as you said. For all the other steps, the evaluation should be the evaluation of the best next step with a small decay.
user avatar
1 vote

Classifying non-labeled data with high dimensionality

This is supposed to be a comment but I haven't got enough reputation to do that. In addition to what @the complexitytheorist has said, I recommend you to have a deeper look at your data first, using ...
user avatar
1 vote

Classifying non-labeled data with high dimensionality

I would recommend to have a look at Finding Groups in Data, which is a very readable introduction to clustering methods. It gives a good overview over a number of different algorithms, both ...
user avatar
  • 5,062
1 vote

How can I evaluate the performance of a system that generates text?

Human evaluation is the gold standard as stated in this podcast by Asli Celikyilmaz, even if you only test a very small part of the generated text. You needed an automated method and this one: BLEURT ...
user avatar
1 vote

How can I evaluate the performance of a system that generates text?

This is a tricky issue. I assume you are using transition probabilities to pick the next suitable word, so you could use some other corpus data, derive probabilities from it, and compare those to ...
user avatar
  • 5,062

Only top scored, non community-wiki answers of a minimum length are eligible