ann人工神经网络_深度学习-人工神经网络(ANN)

ann人工神经网络

Building your first neural network in less than 30 lines of code.

用不到30行代码构建您的第一个神经网络。

1.What is Deep Learning ?

1.什么是深度学习?

Deep learning is that AI function which is able to learn features directly from the data without any human intervention ,where the data can be unstructured and unlabeled.

深度学习是AI功能,它可以直接从数据中学习特征,而无需任何人工干预,其中数据可以是非结构化和无标签的。

1.1 Why deep learning?

1.1为什么要深度学习?

ML techniques became insufficient as the amount of data is increased. The success of a model heavily relied on feature engineering till last decade where these models fell under the category of Machine learning. Where deep learning models deals with finding these features automatically from the raw data.

随着数据量的增加,机器学习技术变得不足。 模型的成功很大程度上取决于特征工程,直到上个十年,这些模型都属于机器学习范畴。 深度学习模型负责处理从原始数据中自动查找这些功能的地方。

1.2 Machine learning vs Deep learning

1.2机器学习与深度学习

ann人工神经网络_深度学习-人工神经网络(ANN)_第1张图片
ML vs DL (Source: https://www.kaggle.com/kanncaa1/deep-learning-tutorial-for-beginners) ML与DL(来源: https : //www.kaggle.com/kanncaa1/deep-learning-tutorial-for-beginners )

2.What is Artificial neural network?

2.什么是人工神经网络?

2.1 Structure of a neural network:

2.1神经网络的结构:

In a neural network as the structure says there is at least one hidden layer between the input and output layers. The hidden layers does not see the inputs. The word “deep” is a relative term which means how many hidden layer a neural network have.

如结构所说,在神经网络中,输入层和输出层之间至少有一个隐藏层。 隐藏的层看不到输入。 术语“深层”是一个相对术语,表示神经网络具有多少个隐藏层。

While computing the layer the input layer is ignored. For example in the picture below we have a 3 layered neural network as mentioned input layer is not counted.

在计算层时,将忽略输入层。 例如,在下面的图片中,我们有一个3层神经网络,因为未提及输入层。

Layers in an ANN:

ANN中的层:

1 Dense or fully connected layers

1密集或完全连接的层

2 Convolution layers

2个卷积层

3 Pooling layers

3个池化层

4 Recurrent layers

4个循环层

5 Normalization layers

5个标准化层

6 Many others

6很多

Different layers performs different type of transformations on the input. A convolution layer mainly used to perform convolution operation while working with image data. A Recurrent layer is used while working with time series data. A dense layer is a fully connected layer. In a nutshell each layer have its own features and used to perform specific task.

不同的层对输入执行不同类型的转换。 卷积层主要用于在处理图像数据时执行卷积运算。 在处理时间序列数据时,将使用循环层。 致密层是完全连接的层。 简而言之,每一层都有自己的功能,并用于执行特定任务。

ann人工神经网络_深度学习-人工神经网络(ANN)_第2张图片
Structure of a neural network (Source : https://www.gabormelli.com/RKB/Neural_Network_Hidden_Layer) 神经网络的结构(来源 https : //www.gabormelli.com/RKB/Neural_Network_Hidden_​​Layer )

2.2 Structure of a 2 layer neural network:

2.2 2层神经网络的结构:

ann人工神经网络_深度学习-人工神经网络(ANN)_第3张图片
structure of a 2 layer neural network (Source : https://ibb.co/rQmCkqG) 2层神经网络的结构 (来源 https : //ibb.co/rQmCkqG )

Input layer : Each of the nodes in the input layer represents the individual feature from each sample within our data set that will pass to the model.

输入层输入层中的每个节点代表数据集中每个样本的独立要素,这些要素将传递给模型。

Hidden layer :The connections between the input layer and hidden layer , each of these connections transfers output from the previous units as input to the receiving unit. Each connections have its own assigned weight. Each input will be multiplied by the weights and output will be an activation function of these weighted sum of inputs.

隐藏层 :输入层和隐藏层之间的连接,这些连接中的每一个都将先前单元的输出作为输入传输到接收单元。 每个连接都有自己分配的权重。 每个输入将乘以权重,输出将是这些输入加权总和的激活函数。

To recap we have weights assigned to each connections and we compute the weighted sum that points to the same neuron(node) in the next layer. That sum is passed as an activation function that transforms the output to a number that can be between 0 and 1.This will be passed on to the next neuron(node) to the next layer. This process occurs over and over again until reaching the output layer.

概括地说,我们为每个连接分配了权重,并计算了指向下一层中相同神经元(节点)的加权总和。 该和作为激活函数传递,该函数将输出转换为介于0到1之间的数字。这将传递到下一个神经元(节点)。 此过程一遍又一遍,直到到达输出层。

Lets consider part1 connections between input layer and hidden layer , as from fig above. Here the activation function we are using is tanh function.

让我们考虑输入层和隐藏层之间的part1连接,如上图所示。 在这里,我们使用的激活函数是tanh函数。

Z1 = W1 X + b1

Z1 = W1 X + b1

A1 = tanh(Z1)

A1 = tanh(Z1)

Lets consider part 2 connections between hidden layer and output layer , as from fig above. Here the activation function we are using is sigmoid function.

让我们考虑隐藏层和输出层之间的第2部分连接,如上图所示。 在这里,我们使用的激活函数是S型函数。

Z2 = W1 A1 + b2

Z2 = W1 A1 + b2

A2 = σ(Z2)

A2 =σ(Z2)

During this process weights will be continuously changing in order to reach optimized weights for each connections as the model continues to learn from the data.

在此过程中,随着模型继续从数据中学习,权重将不断变化,以达到每个连接的最佳权重。

Output layer : If it’s a binary classification problem to classify cats or dogs the output layer have 2 neurons. Hence the output layer can be consists of each of the possible outcomes or categories of outcomes and that much of neurons.

输出层 :如果对猫或狗进行分类是二进制分类问题,则输出层具有2个神经元。 因此,输出层可以由每种可能的结果或结果类别以及大量的神经元组成。

Please note that number of neurons in the hidden layer is a hyper parameter like learning rate.

请注意,隐藏层中神经元的数量是学习率之类的超参数。

3. Building your first neural network with keras in less than 30 lines of code

3.用不到30行代码用keras构建您的第一个神经网络

3.1 What is Keras ?

3.1什么是Keras?

There is a lot of deep learning frame works . Keras is a high-level API written in Python which runs on-top of popular frameworks such as TensorFlow, Theano, etc. to provide the machine learning practitioner with a layer of abstraction to reduce the inherent complexity of writing NNs.

有很多深度学习框架作品。 Keras是用Python编写的高级API,它在TensorFlow,Theano等流行框架之上运行,从而为机器学习从业人员提供了一层抽象层,以减少编写NN的固有复杂性。

3.2 Time to work on GPU:

3.2使用GPU的时间:

In this we will be using keras with Tensorflow backend. We will use pip commands to install on Anaconda environment.

在本文中,我们将使用具有Tensorflow后端的keras。 我们将使用pip命令在Anaconda环境上安装。

· pip3 install Keras

·pip3安装Keras

· pip3 install Tensorflow

·pip3安装Tensorflow

Make sure that you set up GPU if you are using googlecolab

如果您使用的是googlecolab,请确保已设置GPU

ann人工神经网络_深度学习-人工神经网络(ANN)_第4张图片
google colab GPU activation Google colab GPU激活

We are using MNIST data set in this tutorial. The MNIST database of handwritten digits, available from this page, has a training set of 60,000 examples, and a test set of 10,000 examples. It is a subset of a larger set available from MNIST. The digits have been size-normalized and centered in a fixed-size image.

在本教程中,我们将使用MNIST数据集。 可以从此页面获得的MNIST手写数字数据库的训练集为60,000个示例,而测试集为10,000个示例。 它是MNIST可用的较大集合的子集。 这些数字已进行尺寸规格化,并在固定尺寸的图像中居中。

We are importing necessary modules

我们正在导入必要的模块

ann人工神经网络_深度学习-人工神经网络(ANN)_第5张图片

Loading the data set as training & test

加载数据集作为培训和测试

ann人工神经网络_深度学习-人工神经网络(ANN)_第6张图片

Now with our training & test data we are ready to build our Neural network.

现在,有了我们的培训和测试数据,我们就可以构建我们的神经网络了。

ann人工神经网络_深度学习-人工神经网络(ANN)_第7张图片

In this example we will be using dense layer , a dense layer is nothing but fully connected neuron. Which means each neuron receives input from all the neurons in previous layer. The shape of our input is [60000,28,28] which is 60000 images with a pixel height and width of 28 X 28.

在此示例中,我们将使用密集层,密集层仅是完全连接的神经元。 这意味着每个神经元都从上一层中的所有神经元接收输入。 输入的形状为[60000,28,28],它是60000张图像,像素的高度和宽度为28 X 28。

784 and 10 refers to dimension of the output space , which will become the number of inputs to the subsequent layer.We are solving a classification problem with 10 possible categories (numbers from 0 to 9). Hence the final layer has potential output of 10 units.

784和10表示输出空间的尺寸,它将成为下一层的输入数量。我们正在解决一个具有10个可能类别的分类问题(数字从0到9)。 因此,最后一层的潜在输出为10个单位。

Activation function can be different type , relu which is most widely used. In the output layer we are using softmax here.

激活功能可以是使用最广泛的不同类型的relu。 在输出层中,我们在这里使用softmax。

As out neural network is defined we are compiling it with optimizer as adam,loss function as categorical_cross entropy,metrics as accuracy here. These can be changed based upon the need.

由于定义了神经网络,我们在这里使用优化器将其编译为adam,损失函数作为categorical_cross熵,度量作为精度。 这些可以根据需要进行更改。

AIWA !!! You have just build your first neural network.

AIWA !!! 您刚刚建立了第一个神经网络。

There is questions in your mind related to the terms which we have used on model building , like relu,softmax,adam ..these requires in depth explanations I would suggest you to read the book Deep Learning with Python by Francois Chollet, which inspired this tutorial.

您的思维中存在与我们在模型构建中使用的术语相关的问题,例如relu,softmax,adam ..这些需要进行深入的解释,我建议您阅读Francois Chollet撰写的《用Python进行深度学习》一书,这启发了这一点。教程。

We can reshape our data set and split in between train 60000 images and test of 10000 images

我们可以重塑我们的数据集,并在训练60000张图像和10000张图像的测试之间进行划分

Image for post

We will use categorical encoding in order to return number of features in numerical operations.

我们将使用分类编码,以便在数值运算中返回特征数量。

Image for post

Our data set is split into train and test , our model is compiled and data is reshaped and encoded. Next step is to train our neural network(NN).

我们的数据集分为训练和测试,我们的模型被编译,数据被重塑和编码。 下一步是训练我们的神经网络(NN)。

ann人工神经网络_深度学习-人工神经网络(ANN)_第8张图片

Here we are passing training images and train labels as well as epochs. One epoch is when an entire data set is passed forward and backward through the neural network only once.Batch size is number of samples that will propagate through the neural network.

在这里,我们传递训练图像和训练标签以及历元。 一个时期是整个数据集仅通过神经网络向前和向后传递一次,批大小是将通过神经网络传播的样本数量。

ann人工神经网络_深度学习-人工神经网络(ANN)_第9张图片

We are measuring the performance of our model to identify how well our model performed. You will get a test accuracy of around 98 which means our model has predicted the correct digit while 98 percentage of time while running its tests.

我们正在测量模型的性能,以确定模型的性能。 您将获得大约98的测试准确性,这意味着我们的模型在运行测试时的98%的时间里预测了正确的数字。

This is how the first look of a neural network is. That’s not the end just a beginning before we get a deep dive into different aspects of neural networks. You have just taken the first step towards your long and exciting journey.

这就是神经网络的外观。 那不是结束,而是我们深入研究神经网络各个方面之前的开始。 您刚刚迈出了漫长而令人兴奋的旅程的第一步。

Stay focused , keep learning , stay curious.

保持专注,保持学习,保持好奇心。

“Don’t take rest after your first victory because if you fail in second, more lips are waiting to say that your first victory was just luck.” — Dr APJ Abdul Kalam

“第一场胜利后不要休息,因为如果第二场失败,就会有更多的嘴唇在等待说你的第一场胜利只是运气。” — APJ Abdul Kalam博士

Reference : Deep Learning with Python , François Chollet , ISBN 9781617294433

参考:用Python进行深度学习,FrançoisChollet,ISBN 9781617294433

Stay connected — https://www.linkedin.com/in/arun-purakkatt-mba-m-tech-31429367/

保持联系-https://www.linkedin.com/in/arun-purakkatt-mba-m-tech-31429367/

翻译自: https://medium.com/analytics-vidhya/deep-learning-artificial-neural-network-ann-13b54c3f370f

ann人工神经网络

你可能感兴趣的:(python,tensorflow,机器学习,神经网络)