Saul_goodman
Reputation: 141
Can we add conditions to the output of a deep neural network?
I am currently working on a clinical NER tagging application (CliNER - Clinical Named Entity Recognition system) and I am using a Bi-Directional LSTM built with Keras / Tensorflow backend for this task.
I want to know whether there is any method for adding a condition to the output.
For E.X. if the previous output was B-Medicine my next should definitely
I-Medicine or Other and not some random tag like B-Body-Part.
Is there a way to accomplish this?
Upvotes: 2
Views: 194
Answers (0)
Related Questions
- How to constrain a neural network model's output in Rapidminer to non-negative values?
- Preparing input data for LSTM layer with conditions
- Is there a way to add constraints to a neural network output but still with softmax activation function?
- LSTM with Condition
- Incorporate side conditions into Keras neural network
- Concatenate outputs of LSTM in Keras
- How to generate more than 1 output per input in LSTM?
- LSTM Keras API predicting multiple outputs
- Is conditional computing possible with Tensorflow?
- Can I use next layer's output as current layer's input by Keras?