Which activation function is used by the Matlab Convolutional Neural Network Toolbox for the Fully-Connected-Layer?

2 次查看（过去 30 天）
nanocorex
nanocorex 2017-4-21
回答： Taylor Smith 2017-6-27
especially if it is essentially a Multi-Layer-Perceptron which consists of multiple hidden layers connected to a Softmax-Layer.

请先登录，再回答此问题。

采纳的回答

Greg Heath
Greg Heath 2017-4-23
The MATLAB default converts inputs and targets to the [ -1, 1] range. However, this does not help in detecting outliers that should be modified or removed.
In order to detect outliers and prevent saturating hidden nodes, I generally advise converting inputs (and non-classifier targets) to zero- mean/unit-variance and using tansig (i.e., tanh) hidden nodes.
Hope this helps
Thank you for formally accepting my answer
Greg

更多回答（1 个）

Taylor Smith
Taylor Smith 2017-6-27
I have this question as well, however I need to actually know what activation/transfer function is used and ideally where it might be located in source code. Following execution of a simple network line-by-line, I see how the fully connected layer multiplies the input by the appropriate weights and adds the bias, however as far as I can see this is all that is done to calculate the activations for the fully connected layer. The weighted and biased inputs don't seem to be fed to any transfer function.
Any clues?

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by