The Gradient Descent

File, posted without a caption

Kubernetes from 0 to hero by Microsoft - free learning course. https://azure.microsoft.com/en-us/resources/kubernetes-learning-path/

#code #python There is a nice Docker template for ML projects that can be found in this git repository with instructions on how to set it up 🙂 Docker is an essential tool to know - it ensures that your ML model can be executed on any machine without any problems.

#python #programming #careers Happy New Year, everyone! While you are forming your development plan for 2021, I’d like to share some useful tips related to programming that might help you land your dream job. - Use GitHub/GitLab for your portfolio: create repositories with interesting projects that recruiters can look at. Note the word "interesting": it excludes projects where you build something straightforward, l…

#books #python #programming Programming in Python is not an extraordinary thing anymore, but using clean code techniques to, e.g., build a pipeline or an algorithm is something that occurs rarely. If you are eager to learn how to use clean code techniques, the Clean Code book by Robert Cecil Martin is a must-read. Although it's not necessarily related to the Data Science world, it is considered a good guide to clean…

#courses An outstanding course on Inferential Statistics from University of Amsterdam on Coursera. It covers all the fundamentals (and slightly more) that you need to know to start learning ML

#careers Who Is An Ideal Data Scientist? Having been selecting DS and ML engineers myself, I’ve decided to write a small text on what is and what is not a good DS. If I had your CV, I’d automatically screen it for the two main parts: (1) Technical Knowledge and (2) Relevant Projects. 1. Technical Knowledge: that is about the number of programming languages and tools you know and use. I divide technical knowledge…

IBM Cognitive Class AI is quite a useful source that contains free and intense trainings on different fields. I’d explore Data Science with Python specialization.

#mindmaps It's crucial to understand a high-level picture of a typical Data Science project, especially for new-joiners in the field. Personally, I divide any data-related project into two parts: Data Preprocessing and Model Building. Each part has subsequent steps to perform. I've decided to visualize what I call the Data Science Pipeline.

#mindmaps Algorithms Mind Map for beginners 🙂

#code #python Long time ago I've created a git repository with templates of different supervised learning algorithms: Classification 1. Neural Network Classifier 2. Linear Support Vector Machines (LSVM) 3. Logistic Regression 4. Multiclass Classification 5. Kernelized Support Vector Machines (SVM) 6. Decision Trees 7. Naive Bayes Classifiers 8. Random Forests Regression 1. Neural Network Regressor 2. Rid…

#books If you have a good mathematical background and have had some experience in Data Science, you could read ‘Deep Learning’ by Ian Goodfellow, it’s considered as a very good resource that covers Neural Nets and ML in general.