Inspired by Machine Learning for Software Engineers & How to learn Deep Learning in 6 months
This is my multi-month study plan to become machine learning engineer.
I have a Software Engineering degree, not a Computer Science degree. I have an itty-bitty amount of basic knowledge about: Calculus, Linear Algebra, Discrete Mathematics, Probability & Statistics from university.
"We learn driving a car — by driving. Not by learning how the clutch and the internal combustion engine work." When learning machine learning(AI), I'm following the same top-down approach.
I take one subject from the list below, read and google it, run code and take notes. I will forget most of the learnt material, so I make flashcards. I use Anki to review on my phone, wherever I am.
※ Some subjects in Japanese
Details
- Chapter5.Understand Your Data With Descriptive Statistics
- Chapter6.Understand Your Data With Visualization
- Chapter7.Prepare Your Data For Machine Learning
- Chapter8. Feature Selection For Machine Learning
- Chapter9.Evaluate Performance Machine Learning Algorithms Resamling
- Chapter10.Machine Learning Algorithm Performance Metrics
- Chapter11.Spot Check Classification Algorithms
- Chapter12.Spot-Check Regression Algorithms Do
- Chapter13.Compare Machine Learning Algorithms
- Chapter14.Automate Machine Learning Workflows With Pipelines
- Chapter15.Improve Performance with Ensembles
- [Chapter16.Improve Performance with Algorithm Tuning]
- [Chapter17.Save and Load Machine Learning Models]
- Chapter18.Predictive Modeling Project Template
- Chapter19.Your First Machine Learning Project in Python Step By Step
- [Chapter20.Regression Machine Learning Case Study Project]
- Chapter21.Binary Classification Machine Learning Case Study Project
- A Conceptual Framework for Data Visualization
- Matplotlib basic
- Density and Contour Plots
- PythonDataAnalyticsAndVisualization_Chapter4.Data Visualization
- Matplotlib Scatter plot
- About Feature Scaling and Normalization
- Data Preprocessing
- SCALING, STANDARDIZING, NORMALIZING
- Standardize or Normalize _Examples in Python
- Feature selection for supervised models using SelectKBest
- Guide to training and deploying machine learning models using Python
- Linear Regression on Boston Housing Dataset
Details
- Chapter2.Introduction To Theano
- Chapter3.Introduction to TensorFlow
- Chapter4.Introduction to Keras
- Chapter 5. Project: Develop Large Models on GPUs Cheaply In the Cloud(AWS)
- Chapter6.Crash Course In Multi-Layer Perceptrons
- Chapter7. Develop Your First Neural Network With keras
- Chapter 8. Evaluate The Performance of Deep Learning Models
- Chapter 9. Use Keras Models With Scikit-Learn For General Machine Learning
- Chapter 10. Project:Multiclass Classification Of Flower Species
Long Short Term Memory - Jason Brownlee
Practical Deep Learning for Coders
- Understanding Learning Rates and How It Improves Performance in Deep Learning
- Gradient Descent: All You Need to Know
- Gradient Descent in a Nutshell
I learned the foundations of Deep Learning:Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/He initialization, and more. I worked on case studies from healthcare, autonomous driving, sign language reading, music generation, and natural language processing. I practice all these ideas in Python and in TensorFlow.
I will learn Machine Learning Concepts, Knime, Apache Spark