# How many possible layers can be there in deep neural network?

Table of Contents

- 1 How many possible layers can be there in deep neural network?
- 2 How many hidden layers does a neural network have to have to be a universal Approximator?
- 3 How many hidden layers does CNN have?
- 4 What is the danger to having too many hidden units in your network?
- 5 How to train a neural network with MNIST data?
- 6 Are all layers of a neural network fully connected?

## How many possible layers can be there in deep neural network?

Look forward to the answers of the RG experts. 100 neurons layer does not mean better neural network than 10 layers x 10 neurons but 10 layers are something imaginary unless you are doing deep learning. Dear Duzhen Zhang , There is no maximum number of layers in a deep network.

1 hidden layer

The Universal Approximation Theorem states that a neural network with 1 hidden layer can approximate any continuous function for inputs within a specific range. If the function jumps around or has large gaps, we won’t be able to approximate it.

**How many hidden layers are necessary for a neural network to be able to represent any continuous function?**

two hidden layers

Jeff Heaton (see page 158 of the linked text), who states that one hidden layer allows a neural network to approximate any function involving “a continuous mapping from one finite space to another.” With two hidden layers, the network is able to “represent an arbitrary decision boundary to arbitrary accuracy.”

**What is the minimum number of hidden layers a neural network should have to be qualified as a deep neural network?**

More depth means the network is deeper. There is no strict rule of how many layers are necessary to make a model deep, but still if there are more than 2 hidden layers, the model is said to be deep. Q9. A neural network can be considered as multiple simple equations stacked together.

2 Answers. The first layer is the input layer and the last one is the output layer. Whatever comes in between these two are the hidden layers.

If you have too many hidden units, you may get low training error but still have high generalization error due to overfitting and high variance. (overfitting – A network that is not sufficiently complex can fail to detect fully the signal in a complicated data set, leading to underfitting.

**How does neural network determine hidden layers?**

The number of hidden neurons should be between the size of the input layer and the size of the output layer. The number of hidden neurons should be 2/3 the size of the input layer, plus the size of the output layer. The number of hidden neurons should be less than twice the size of the input layer.

**How many layers should a convolutional neural network have?**

three layers

Convolutional Neural Network Architecture A CNN typically has three layers: a convolutional layer, a pooling layer, and a fully connected layer.

## How to train a neural network with MNIST data?

10 examples of the digits from the MNIST dataset, scaled up 2x. For training the neural network, we will use stochastic gradient descent; which means we put one image through the neural network at a time. Let’s try to define the layers in an exact way.

## Are all layers of a neural network fully connected?

All layers will be fully connected. We are making this neural network, because we are trying to classify digits from 0 to 9, using a dataset called MNIST, that consists of 70000 images that are 28 by 28 pixels. The dataset contains one label for each image, specifying the digit we are seeing in each image.

**How accurate is the MNIST handwriting recognition neural network?**

The size of the network (number of neurons per layer) is dynamic. It’s accuracy in classifying the handwritten digits in the MNIST database improved from 85\% to >91\%. In a previous blog post I introduced a simple 1-Layer neural network for MNIST handwriting recognition .

**What is the MNIST data set used for?**

The MNIST database of handwritten digits is one of the most wi d ely used data sets used to explore Neural Networks and became a benchmark for model comparison. More recently, Zalando research published a new dataset, with 10 different fashion products.