You will be an engineer in 100 days ――Day 84 ――Programming ――About machine learning 9

Click here until yesterday

You will become an engineer in 100 days --Day 76 --Programming --About machine learning

You will become an engineer in 100 days-Day 70-Programming-About scraping

You will become an engineer in 100 days --Day 66 --Programming --About natural language processing

You will become an engineer in 100 days --Day 63 --Programming --Probability 1

You will become an engineer in 100 days-Day 59-Programming-Algorithms

You will become an engineer in 100 days --- Day 53 --Git --About Git

You will become an engineer in 100 days --Day 42 --Cloud --About cloud services

You will become an engineer in 100 days --Day 36 --Database --About the database

You will be an engineer in 100 days-Day 24-Python-Basics of Python language 1

You will become an engineer in 100 days --Day 18 --Javascript --JavaScript basics 1

You will become an engineer in 100 days --Day 14 --CSS --CSS Basics 1

You will become an engineer in 100 days --Day 6 --HTML --HTML basics 1

This time is a continuation of the story about machine learning. I would like to touch on deep learning.

About deep learning

I will explain what you can do with machine learning for the first time, but what you can do with machine learning There are basically three.

・ Regression ・ Classification ・ Clustering

Roughly speaking, it becomes prediction, but the part of what to predict changes.

・ Regression: Predict numerical values ・ Classification: Predict categories ・ Clustering: Make it feel good

In machine learning, there is a learning model that predicts something. One of these learning models is called a neural network.

About Neural Networks (NN)

It is a mathematical model that aims to express the characteristics of neurons found in brain function. It has a brain-like structure.

スクリーンショット 2020-06-12 18.09.14.png

The structure is divided into an input layer, an intermediate layer (hidden layer), and an output layer.

For example, suppose you want to predict gender, male or female. It becomes a model for classifying categorical values, and gives numerical values of explanatory variables to the input layer. After calculating nicely in the middle layer, as a result in the output layer It spits out numerical values such as 0.XX for men and 0.YY for women.

Basically, it will be judged by the size of the numerical value The category with the highest number is the predicted value.

If this is the mechanism of neural network (NN) and becomes deep neural network (DNN) There are two or more hidden layers.

スクリーンショット 2020-06-12 18.09.21.png

Learning using deep neural network isdeep learning (DL) Deep learning is a form included in machine learning.

How neural networks work

As shown in the figure above, it has a shape that imitates the brain structure, but in each unit part Numerical calculation is performed using a function called activation function.

スクリーンショット 2020-06-12 18.19.22.png

Receives numbers from the previous layer and passes them to the next layer. The functions used at that time are as follows.

Step function: Returns 0 or 1 at any threshold Sigmoid function Returns a continuous value from 0 to 1 Relu function: Returns the value when it is greater than or equal to 0, and returns 0 when it is less than 0.

We will perform multi-layered calculations by specifying an activation function that feels like this.

High-dimensional expression is possible by increasing the number of hidden layers Processing of learning data It is said that a certain degree of accuracy can be achieved without specifying the features in detail.

Disadvantages of deep learning

With a normal model, you can calculate which item contributed, etc. There is a point that it is difficult to understand in deep learning.

In addition, it requires a large amount of calculation compared to other models and consumes a large amount of calculation resources. Therefore, a lot of computational resources are required when using long data.

About the derivative model of the neural network

** Convolutional Neural Network (CNN) **

With a neural network suitable for capturing features such as images We have introduced a convolution layer and a pooling layer into traditional networks.

A convolution is a mathematical operation that applies one function to another in some way. Pooling is to extract one numerical value from numerical data.

This CNN has demonstrated high performance in image analysis.

In recent years, he has achieved almost human-level performance in object recognition tasks. Their error rates continue to decline year by year, with current image classification tasks. We have a record with an error rate of less than 3%.

This is even more than human performance for the same task Since it is a low number, it exceeds human accuracy.

Because there is a possibility of drawing out performance that exceeds human accuracy in this way It is a translation that is drawing attention.

Summary

When non-engineers suddenly try to understand deep learning I think the hurdles are quite high.

Especially when it comes to implementation.

First of all, understand the rough mechanism and the meaning of the words If you can do that, I think you should move on.

For the time being, let's suppress words related to deep learning.

16 days until you become an engineer

Author information

Otsu py's HP: http://www.otupy.net/

Youtube: https://www.youtube.com/channel/UCaT7xpeq8n1G_HcJKKSOXMw

Twitter: https://twitter.com/otupython

Recommended Posts

You will be an engineer in 100 days ――Day 81 ――Programming ――About machine learning 6
You will be an engineer in 100 days ――Day 82 ――Programming ――About machine learning 7
You will be an engineer in 100 days ――Day 79 ――Programming ――About machine learning 4
You will be an engineer in 100 days ――Day 76 ――Programming ――About machine learning
You will be an engineer in 100 days ――Day 80 ――Programming ――About machine learning 5
You will be an engineer in 100 days ――Day 78 ――Programming ――About machine learning 3
You will be an engineer in 100 days ――Day 84 ――Programming ――About machine learning 9
You will be an engineer in 100 days ――Day 83 ――Programming ――About machine learning 8
You will be an engineer in 100 days ――Day 77 ――Programming ――About machine learning 2
You will be an engineer in 100 days ――Day 85 ――Programming ――About machine learning 10
You will be an engineer in 100 days ――Day 71 ――Programming ――About scraping 2
You will be an engineer in 100 days ――Day 61 ――Programming ――About exploration
You will be an engineer in 100 days ――Day 74 ――Programming ――About scraping 5
You will be an engineer in 100 days ――Day 73 ――Programming ――About scraping 4
You will be an engineer in 100 days ――Day 75 ――Programming ――About scraping 6
You will be an engineer in 100 days --Day 68 --Programming --About TF-IDF
You will be an engineer in 100 days ――Day 70 ――Programming ――About scraping
You will be an engineer in 100 days --Day 63 --Programming --Probability 1
You will be an engineer in 100 days --Day 65 --Programming --Probability 3
You will be an engineer in 100 days --Day 64 --Programming --Probability 2
You will be an engineer in 100 days --Day 86 --Database --About Hadoop
You will be an engineer in 100 days ――Day 60 ――Programming ――About data structure and sorting algorithm
You will be an engineer in 100 days --Day 27 --Python --Python Exercise 1
You will be an engineer in 100 days --Day 34 --Python --Python Exercise 3
You will be an engineer in 100 days --Day 31 --Python --Python Exercise 2
You become an engineer in 100 days ――Day 67 ――Programming ――About morphological analysis
You become an engineer in 100 days ――Day 66 ――Programming ――About natural language processing
You will be an engineer in 100 days ――Day 24 ―― Python ―― Basics of Python language 1
You will be an engineer in 100 days ――Day 30 ―― Python ―― Basics of Python language 6
You will be an engineer in 100 days ――Day 25 ―― Python ―― Basics of Python language 2
You will be an engineer in 100 days --Day 29 --Python --Basics of the Python language 5
You will be an engineer in 100 days --Day 33 --Python --Basics of the Python language 8
You will be an engineer in 100 days --Day 26 --Python --Basics of the Python language 3
You will be an engineer in 100 days --Day 35 --Python --What you can do with Python
You will be an engineer in 100 days --Day 32 --Python --Basics of the Python language 7
You will be an engineer in 100 days --Day 28 --Python --Basics of the Python language 4
Become an AI engineer soon! Comprehensive learning of Python / AI / machine learning / deep learning / statistical analysis in a few days!
You have to be careful about the commands you use every day in the production environment.
Build an interactive environment for machine learning in Python
About testing in the implementation of machine learning models
About machine learning overfitting
Programming learning record day 2
Until an engineer who was once frustrated about machine learning manages to use machine learning at work
[Machine learning] Let's summarize random forest in an easy-to-understand manner
Machine learning in Delemas (practice)
An introduction to machine learning
About machine learning mixed matrices
Python Machine Learning Programming> Keywords
Used in machine learning EDA
How about Anaconda for building a machine learning environment in Python?
Learn machine learning anytime, anywhere in an on-demand Jupyter Notebook environment