2018 plan for getting expertise in Machine Learning and Deep Learning
Machine Learning and deep learning are next frontier in the world of innovation. These skill sets are high in demand and demand is going to increase further as we are moving towards a world with connected systems.
Although I am experienced professional with SAS having multiple SAS certifications and using SAS for programming, predictive model building, optimization and data visualization for more than seven years, I will be foolish I do not recognize how important it is to adopt open source platforms for innovation.
2018 plan to acquire expertise in these are are
1. Choose a programming language and I have chose python as my language of preference
2. Do hands on practice to be efficient in Pandas and Numpy. These two libraries are useful and very important for data exploration,wrangling and data cleaning. I find Kernals in Kaggle and below blogs and books to be helpful tutorial for Pandas
a. https://www.dataquest.io/blog/pandas-tutorial-python-1/
b.https://www.dataquest.io/blog/pandas-tutorial-python-2/
c. https://www.kaggle.com/kanncaa1/data-sciencetutorial-for-beginners
d. Python for Data Analysis book by Wes McKiney
3. Take up an example problem. Understand the Sci-kit or sklearn package of python. Implement different algorithms available to your problem. You can consider problems in Kaggle.com or from any other source. It will be ideal to start with a binary prediction problem.
a. Data Science from scratch a book by Joel Grus
b. Focus Logistic Regression, Decision Tree, Random Forest Classifier, Gradient Boosting Classifier, Gaussian Naive Bayes Classifier. Spend time in learning and understanding difference between these algorithms
4. While having good understanding of algorithms and its application is important, data wrangling and treatment plays significant role in the development of accurate model
a. Based on the data and business problem, create features or independent variables
b. Apply proper missing value treatment
c. Outlier treatment and variable transformations helps in eliminating biases in the model
d. learn how to use python packages for feature extractions
f. Eliminate multi coli-linearity from the model
5. Learn neural network, convoluted neural network and understand Tensorflow framework for deep learning
Taking up rigorous and regular exercises on the above topic will help you in having career in the area if data science and machine learning.
thanks
Lokendra
3. Take up an example problem. Understand the Sci-kit or sklearn package of python. Implement different algorithms available to your problem. You can consider problems in Kaggle.com or from any other source. It will be ideal to start with a binary prediction problem.
a. Data Science from scratch a book by Joel Grus
b. Focus Logistic Regression, Decision Tree, Random Forest Classifier, Gradient Boosting Classifier, Gaussian Naive Bayes Classifier. Spend time in learning and understanding difference between these algorithms
4. While having good understanding of algorithms and its application is important, data wrangling and treatment plays significant role in the development of accurate model
a. Based on the data and business problem, create features or independent variables
b. Apply proper missing value treatment
c. Outlier treatment and variable transformations helps in eliminating biases in the model
d. learn how to use python packages for feature extractions
f. Eliminate multi coli-linearity from the model
5. Learn neural network, convoluted neural network and understand Tensorflow framework for deep learning
Taking up rigorous and regular exercises on the above topic will help you in having career in the area if data science and machine learning.
thanks
Lokendra
Comments
Post a Comment