The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
"How many hidden layers should be used in Neural Net?"
Is there any method by which I can check that this many Hidden layers and Neurons are best suitable for this model?
Tagged:
0
Best Answer
-
varunm1 Member Posts: 1,207 UnicornHi @vjmeena
There is no thumb rule for a number of layers in neural networks. In my works, I generally build complex neural networks (with more layers) if there are many data samples. For, small datasets neural net with fewer layers would suffice. Try different combinations and observe the performance metrics. Based on that you can see which is best.
You can also try AutoMLP which gets an optimal number of neurons based on training different networks in parallel.
Performance of neural nets is mainly influenced by parameters like activation functions, learning rates, drop out etc.
Regards,
Varun
https://www.varunmandalapu.com/Be Safe. Follow precautions and Maintain Social Distancing
7