🛠️ Scheduled Maintenance | We’ll be undergoing scheduled maintenance and upgrades between 00:00 PST Jan 26th until 00:00 PST Jan 28th. There may be brief interruption of services in that period. We apologize for the inconvenience.

×
The 365 Data Science team is proud to invite you to our own community forum. A very well built system to support your queries, questions and give the chance to show your knowledge and help others in their path of becoming Data Science specialists.
Ask
Anybody can ask a question
Answer
Anybody can answer
Vote
The best answers are voted up and moderated by our team

Optimizers

Back to all questions

Optimizers

1 year ago
Vote Up Vote Down
0
Votes
1
Answer

Hello,
I am stuck on a case study and I will be so thankful if you can help.
I am building an algorithm for predicting one output of a chemical plant with 4 inputs and 3 neurons in the hidden layer, I have to use [Broyden–Fletcher–Goldfarb–Shanno (BFGS) optimization algorithm], but I can’t find it in tensorflow. I know that There is  TensorFlow SciPy Optimizer interface which can be used for an access to optimizers like the BFGS, but I don’t know how to use it. Can you please tell me how to import other additional optimizers in tensorflow?
Thank you in advance.
Waiting for your reply.
Kind Regards.

1 Answer

365 Team 1 year ago
Vote Up Vote Down
0
Votes

Hi Hady,
Thanks for reaching out!
What you are suggesting is a good option for new optimizers. However, I found that there is an already available optimizer you can employ: tfp.optimizer.bfgs_minimize.
It is a part of the tensorflow-probability package. I’d suggest installing it and trying out the built-in optimizers.
Best,
Iliya

You must to answer this question.