# Tag Info

5

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. This is the application you refer to, another context it’s useful is swarm control (for drone swarms, for example). While this is technically ALife, as far as I’m ...

3

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 a Ph.D., you're expected to come up with new ideas/tools), then you won't probably need to know C++, as the most commonly used libraries for machine learning ...

3

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 reproduce the results. If you want something more similar to the model.summary() method you mention, TensorBoard Graph Dashboard might help.

2

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 programming in Scala, Java, Groovy, and now Lisp; I didn't really know any of these languages before my working with them (except for Java). But I have been able ...

2

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 probably the approach most take now of days when going the GAN route. Note that just basic MLE training has shown promise with openAI's GPT2. When i need a text ...

2

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 tutorial.

2

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 can be used to compares actions but they are not very meaningful in representing performance of the agent since you have nothing to compare them with. You don't ...

1

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.

1

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 dimension reduction and visualisation methods such as PCA and t-SNE. A better understanding of data may always save you a lot of work. Then you can choose ...

1

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 agglomerative and hierarchical. As far as I remember, source code for the various algorithms is available on the web somewhere. I am sure you will find a fitting ...

1

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 by Google would be helpful. It's a flexible, semantic-level metric/model trained in a multi-stage way: 1) masked language model like BERT; 2) pre-training on ...

1

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 your system. Not very satisfactory, though, as you might end up evaluating the system in a circular way, deriving your test data in the same way as you generate ...

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