https://github.com/SeongjooHong/jupyter-notebook/blob/master/cost%20function%20and%20graduent%20descent%20and%20python%20class%20study.ipynb
2019.12.28(pm): Regression using scikit-learn diabetes data
https://github.com/SeongjooHong/jupyter-notebook/blob/master/diabetes%20regression%20study.ipynb
2019.12.16(pm): How to Change Jupyter notebook Initial Path Settings
When using the Jupyter notebook, the initial path is often C: \ Users \ USERNAME. In this case, It is difficult to manage python code, and C drives become a mess. So users run Jupyter notebook, go to Desktop, create a new folder and work on it. Because doing this repetitive task every time is …
Continue reading “2019.12.16(pm): How to Change Jupyter notebook Initial Path Settings”
2019.12.16(pm): How to Troubleshoot SSL (HTTP) Issues
If you get the following error code, there is a security problem. The causes can be reduced to three things: communication errors, firewall blocking, and SSL connection restriction. The command to solve is: You may want to reinstall SSL, reinstall previous version of Anaconda. If this doesn’t work, please let me know.
2019.12.15(pm): Virtual Environment Management with Anaconda
If you are using anaconda, you will see that the command is set to base and root. Virtual environment management is essential and important when using Python. Today, let’s look at how to create and manage virtual environments in Anaconda. Here are the commands: To check your Python version, use the bleow command to check …
Continue reading “2019.12.15(pm): Virtual Environment Management with Anaconda”
2019.12.14(pm): Motion Control Car with flex sensor and Xbee module
Let’s create a moving RC car using hand gestures. I made it using flex sensor and Xbee communication module. Materials Hardware – glove with flex sensor and transmitter Hardware – RC car with receiver XCTU Circuit Design for glove Code –
2019.12.10(pm): RNN(Recurrent Neural Network)
Neural networks that process sequential data must have three functions: Temporality: Features must be entered one at a time in order. Variable length: To process a sample of length n, the hidden layer must appear n times. Context dependency: Remember the previous feature and use it at the right moment. To design a learning model …
Continue reading “2019.12.10(pm): RNN(Recurrent Neural Network)”
2019.12.09(pm): Autoencoder
The autoencoder is a neural network that receives the feature vector x and outputs the same or similar vector x ‘. The figure below shows the structure of an autoencoder. Since the output must be the same as the input, the number of nodes in the output layer and the number of nodes in the …
2019.12.09(am): Back propagation
After the release of Perceptron in 1958, the New York Times published a shocking article on the 8th of July that a computer would be developed that would soon walk, speak, and recognize self. But in 1969, Marvin Minsky devised a multilayer perceptron (MLP) to solve the XOR problem, and said there is no way …
2019.12.08(pm): Multi-Layer Perceptron
Perceptron has the limitation that it can only handle situations where linear separation is possible. The problem of XOR classification is that the perceptron has a 75% accuracy rate because one sample is wrong no matter which decision line is used. In 1969, Marvin Minsky’s Perceptrons, the father of artificial intelligence, revealed this fact, and …