[Tutorials] Machine learning & Neural Network

[**:house: Home**](https://hackmd.io/s/rkkDP_l4M) | [:boy: **About**](https://hackmd.io/s/B149Z8v7b) | [**:microscope: Researches**](https://hackmd.io/s/rJPFNKlVz) | [**:rocket: Side projects**](https://hackmd.io/s/H1aS2qe4G) | [**:airplane: Life gallery**](https://hackmd.io/s/HJN4JslNM) [Data science](https://hackmd.io/s/H1aS2qe4G#data-science) **>** [Tutorials] Machine learning & Neural Network --- # [Tutorials] Machine learning & Neural Network *<div style="text-align: center;" markdown="1">`scikit-learn` `numpy` `pandas` `iPython-notebook` `LATEX` `theano`</div>* ## Introduction [Two online tutorials](#tutorials) written by me in bellow are about the fundamental techniques and theories of machine learning and neural network with IPython-notebook. The artificial intelligent (AI) is a popular searching keyword which could be heard in any field, e.g. marketing, robotics, art, biologics, physics analysis etc.. The AI is expected to help the human to solve the complicated problem. It can be categorized to the ***strong AI*** and ***weak AI***. The strong AI is defined the agent can think and act as a human, i.e. it have mind and mental state. But the weak AI can think and act *rationally*, i.e. it act intelligently. The weak AI is much common for applications in nowadays. It can be achieved by several ways to have good performance for solving the problem by building the analytic algorithm, rules, learning models, logic planing etc... <div style="text-align: center;" markdown="1"><img src="https://i.imgur.com/pI7ZaEK.png" height="250"></div> <br> However, making machine to learn models, so called **machine learning (ML)**, is specially being an important and well-known branch in the AI. It is widely useful in handwriting recognition, image recognition, parameters optimization etc.. On the other hand, an advance algorithm, which was purposed in decades, is revived and growing to be a significant learning algorithm now. It is the **Neural Network** (or **Deeplearning**, if the network is much deeper and adding much advance algorithms). Thus the tutorials focus on the basic models of machine learning, and giving the simple fundamental structures of neural network. Since the technologies is improving rapidly, understanding their insight and spirit are very important. The fundamental theories and simple applications are described here. Credited to several great experts around the corners of the world, we are lucky to have several tools and books to learn and approach the knowledges elegantly. The two tutorials are based on the books, [**Python Machine Learning**, *Sebastian Raschka*](https://sebastianraschka.com/books.html) and [**Neural Network And Deeplearning**, *Michael Nielsen*](http://neuralnetworksanddeeplearning.com), which demonstrate the **Machine learning**, **Neural Network** and **Deeplearning**. The contains are also referred to many good materials, details see the **Reference resource**. ## Tutorials **<div style="text-align: center;" markdown="1">**[<img src="https://i.imgur.com/OQfaOHt.png" height="300"><br>**[1] Python Machine Learning**](https://hackmd.io/s/SyGQ-AZNf) <br>*`mathematics` `LATEX` `scikit-learn` `numpy` `pandas` `iPython-notebook`*</div> <br> <br> **<div style="text-align: center;" markdown="1">**[<img src="https://i.imgur.com/GYHPGz3.png" height="200"><br>**[2] Neural network and deeplearning**](https://hackmd.io/s/SyET_0bEz) <br>*`mathematics` `LATEX` `numpy` `pandas` `iPython-notebook` `theano`*</div> ## References - See documents in [Course taking & book reading](https://hackmd.io/s/r16bkjl4f). - Picture credited to <http://www.euclidean.com/data-posts-machine-learning> - Github : <https://github.com/juifa-tsai/workbook_MachineLearning> <br> --- [:ghost: Github](https://github.com/juifa-tsai) | [:busts_in_silhouette: Linkedin ](https://www.linkedin.com/in/jui-fa-tsai-08ba0a93)