How does TensorFlow compute cost in hidden layers?

Christian_Simonis · April 2, 2023, 6:29am

these concepts are very important. In doubt feel free to re-warch the course or ask any open question in this forum.

A cost function provides a metric you can use to improve your optimization. When fitting a model you actually want to minimise the costs, (the model error). See also:

https://towardsdatascience.com/cost-functions-the-underpinnings-of-machine-learning-549ac5edb211

Gradient descent is a powerful method for above mentioned optimization when fitting your model. It is really well explained by Andrew Ng in this video:

Gradient Descent (C1W2L04) - YouTube

Also this thread might be interesting for you:

How different initialization of centroids of K-means results in drastic different clusters ? They all share common cost function - #5 by Christian_Simonis

Topic		Replies	Views
Do we choose cost function only according to the output layer Advanced Learning Algorithms week-2	6	532	August 30, 2022
Neural network regularization: What does it mean to regularize a hidden layer? Advanced Learning Algorithms week-3	4	548	April 3, 2023
Hidden layers in deep neural network Neural Networks and Deep Learning	1	574	June 27, 2021
Gradient decent in a multi layered neural network Advanced Learning Algorithms week-1	3	228	February 21, 2024
Week4- assignment 2- Difference in gradient calculation for the last layer activation in neural networks Neural Networks and Deep Learning	2	674	May 17, 2023

How does TensorFlow compute cost in hidden layers?

Related topics