CODEWITHSUNDEEP
python-3.xtensorflowoptimizationkeras
Juan David
Juan David

Reputation: 460

Design consideration for "recurrent" neural network with Keras and Tensorflow

I am currently working on my grade project. The main goal of this project is to build a AI aided inventory system. My current approach is to use a neural network to "teach" the system how to behave according to its current state (the current inventory) and a pseudorandom demand. The inputs of the net should be the current inventory and the network should output how much the company should order of a given product to minimize both sales losses due to lacking inventory and inventory level (the model should not output crazy amounts because keeping inventory costs money). The outputs from one run should be used to compute the inputs of the next run based on current inventory, current demand and orders(the outputs themselves). The problem I am facing is that I only need an initial state (inventory at time 0) to train the model, but I do not know any ways to set up Keras like this. Maybe someone could point me to a useful resource to take on this problem. To me it looks like I need to define a custom loss function and maybe create a custom layer to the system (I know to to define the function and the inventory update rule, buy I don't know how to tell Keras what to do with them).

Upvotes: 0

Views: 43

Answers (1)

Guillem
Guillem

Reputation: 2647

I don't think that you need to create custom layers or custom losses. IMO the steps you shoul follow are:

  1. Create a dataset where this time correlation between inventory at time t and t - 1 inventory is present.
  2. Decalare a lookback hyperparameter (How many inventories you want to analyse in a single sequence?)
  3. Then you can feed this data to an RNN in order to solve the regression problem (For example a loss for regression is mse).

Check this explainatory notebook written by François Chollet on how to work with RNNs.

Upvotes: 1

Related Questions