Subscribe to DSC Newsletter

I'm new to the data science world, and I hope to solve a problem using deep learning methods, I started learning how FNN and CNN work and when I saw how many models and methods are the I got a bit confused and decided to ask for your help in pointing me at the right direction,

The problem I need to solve: I have a data set which unlabeled and consist of actions taken by a multi-agent system, that will probably contain

Time | Role of Agent | Action taken | Position of agent | outcome ....

I need to train a model\models to detect a strategic sequences of actions (i.e rows in the data) that means that I need a model that will take into consideration not only the current row in data but also the rows that came before (means actions taken by other agents) and if possible rows that will be inputted later.

the output needs to be a classification on the data into strategic plays, such that a play is a few actions that happend one after the other,

the dataset is still unprepared and we are just in the planning and learning stage, by I hope that ow that you understand the problem that I'm facing a bit you can help me decide on a Deep Learning model(or models) that can meet the requirements and preform good for such task, so I can really dig into that model and learn plus if you know of any articles that can be of assistance it will be great as well

Thanks for the help!

Views: 177

Reply to This

Follow Us

Resources

© 2018   Data Science Central ®   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service