Tutorials, Overviews

Latest:

• Training BPE, WordPiece, and Unigram Tokenizers from Scratch using Hugging Face - Oct 21, 2021.
  
  Comparing the tokens generated by SOTA tokenization algorithms using Hugging Face's tokenizers package.

  Tags: Hugging Face, NLP, Python, Tokenization

• How I Tripled My Income With Data Science in 18 Months - Oct 21, 2021.
  
  Over a year ago, I lost my job due to the COVID-19 pandemic. During this this, I taught myself data science and tripled my income.

  Tags: Career Advice, Data Science, Salary

• Simple Question Answering Web App with HuggingFace Pipelines - Oct 21, 2021.
  
  See how easy it can be to build a simple web app for question answering from text using Streamlit and HuggingFace pipelines.

  Tags: Hugging Face, NLP, Question answering, Streamlit

• Data Preparation in R using dplyr, with Cheat Sheet! - Oct 20, 2021.
  
  Leverage the powerful data wrangling tools in R’s dplyr to clean and prepare your data.

  Tags: Cheat Sheet, Data Preparation, R

• Data Science Portfolio Project Ideas That Can Get You Hired (Or Not) - Oct 20, 2021.
  
  Choosing what to include in your data science portfolio during the job search is the most important part of the process. Each project should be well-structured so that a hiring manager can assess your skills quickly. To help you get started, we highlight a few data science project ideas that you should consider for your portfolio.

  Tags: Career Advice, Data Science, Portfolio, Project

• 11 Most Practical Data Science Skills for 2022 - Oct 19, 2021.
  
  While the field of data science continues to evolve with exciting new progress in analytical approaches and machine learning, there remain a core set of skills that are foundational for all general practitioners and specialists, especially those who want to be employable with full-stack capabilities.

  Tags: Career Advice, Data Science Skills, Explainable AI, Feature Engineering, GitHub, NLP, Regression, SQL

• How to Create an Interactive Dashboard in Three Steps with KNIME Analytics Platform - Oct 19, 2021.
  
  In this blog post I will show you how to build a simple, but useful and good-looking dashboard to present your data - in three simple steps!

  Tags: Analytics, Dashboard, Data Visualization, Knime, Platform

• Real Time Image Segmentation Using 5 Lines of Code - Oct 18, 2021.
  
  PixelLib Library is a library created to allow easy integration of object segmentation in images and videos using few lines of python code. PixelLib now provides support for PyTorch backend to perform faster, more accurate segmentation and extraction of objects in images and videos using PointRend segmentation architecture.

  Tags: Computer Vision, Image Processing, Machine Learning, Python, Segmentation

• Serving ML Models in Production: Common Patterns - Oct 18, 2021.
  
  Over the past couple years, we've seen 4 common patterns of machine learning in production: pipeline, ensemble, business logic, and online learning. In the ML serving space, implementing these patterns typically involves a tradeoff between ease of development and production readiness. Ray Serve was built to support these patterns by being both easy to develop and production ready.

  Tags: FastAPI, Machine Learning, Production, Python, Ray

• New Computing Paradigm for AI: Processing-in-Memory (PIM) Architecture - Oct 15, 2021.
  
  As larger deep neural networks are trained on the latest and fastest chip technologies, an important challenge remains that bottlenecks performance -- and it is not compute power. You can try to calculate a DNN as fast as possible, but there is data -- and it has to move. Data pipelines on the chip are expensive and new solutions must be developed to advance capabilities.

  Tags: AI, Hardware, In-Memory Computing, Samsung

• How to calculate confidence intervals for performance metrics in Machine Learning using an automatic bootstrap method - Oct 15, 2021.
  
  Are your model performance measurements very precise due to a “large” test set, or very uncertain due to a “small” or imbalanced test set?

  Tags: Machine Learning, Metrics, Statistics

• Deploying Your First Machine Learning API - Oct 14, 2021.
  
  Effortless way to develop and deploy your machine learning API using FastAPI and Deta.

  Tags: API, Deployment, FastAPI, Machine Learning, Python, spaCy

• The 20 Python Packages You Need For Machine Learning and Data Science - Oct 14, 2021.
  
  Do you do Python? Do you do data science and machine learning? Then, you need to do these crucial Python libraries that enable nearly all you will want to do.

  Tags: Data Science, Keras, Machine Learning, Matplotlib, numpy, Pandas, Plotly, Python, PyTorch, scikit-learn, TensorFlow

• What is Clustering and How Does it Work? - Oct 14, 2021.
  
  Let us examine how clusters with different properties are produced by different clustering algorithms. In particular, we give an overview of three clustering methods: k-Means clustering, hierarchical clustering, and DBSCAN.

  Tags: Clustering, DBSCAN, K-means, Unsupervised Learning

• How to Ace Data Science Interview by Working on Portfolio Projects - Oct 13, 2021.
  
  Recruiters of Data Science professionals around the world focus on portfolio projects rather than resumes and LinkedIn profiles. So, learning early how to contribute and share your work on GitHub, Deepnote, and Kaggle can help you perform your best during data science interviews.

  Tags: Data Science, GitHub, Interview Questions, Kaggle, Portfolio, Project

• Building Multimodal Models: Using the widedeep Pytorch package - Oct 13, 2021.
  
  This article gets you started on the open-source widedeep PyTorch framework developed by Javier Rodriguez Zaurin.

  Tags: Machine Learning, Modeling, Python, PyTorch

• Create Synthetic Time-series with Anomaly Signatures in Python - Oct 12, 2021.
  
  A simple and intuitive way to create synthetic (artificial) time-series data with customized anomalies — particularly suited to industrial applications.

  Tags: Anomalies, Python, Synthetic Data, Time Series

• Step by Step Building a Vacancy Tracker Using Tableau - Oct 12, 2021.
  
  Step-by-step explanations of vacancies valued in tens of millions of dollars in the small town of Fitchburg, Massachusetts.

  Tags: Dashboard, Data Visualization, Tableau

• AutoML: An Introduction Using Auto-Sklearn and Auto-PyTorch - Oct 11, 2021.
  
  AutoML is a broad category of techniques and tools for applying automated search to your automated search and learning to your learning. In addition to Auto-Sklearn, the Freiburg-Hannover AutoML group has also developed an Auto-PyTorch library. We’ll use both of these as our entry point into AutoML in the following simple tutorial.

  Tags: Automated Machine Learning, AutoML, Python, PyTorch, scikit-learn

• Scaling human oversight of AI systems for difficult tasks – OpenAI approach - Oct 11, 2021.
  
  The foundational idea of Artificial Intelligence is that it should demonstrate human-level intelligence. So, unless a model can perform as a human might do, its intended purpose is missed. Here, recent OpenAI research into full-length book summarization focuses on generating results that make sense to humans with state-of-the-art results that leverage scalable AI-enhanced human-in-the-loop feedback.

  Tags: AGI, GPT-3, NLP, OpenAI, Summarization, Text Summarization

• Query Your Pandas DataFrames with SQL - Oct 11, 2021.
  
  Learn how to query your Pandas DataFrames using the standard SQL SELECT statement, seamlessly from within your Python code.

  Tags: Comic, Pandas, Python, SQL

• 8 Must-Have Git Commands for Data Scientists - Oct 8, 2021.
  
  Git is a must-have skill for data scientists. Maintaining your development work within a version control system is absolutely necessary to have a collaborative and productive working environment with your colleagues. This guide will quickly start you off in the right direction for contributing to an existing project at your organization.

  Tags: Advice, Data Scientist, GitHub

• Dealing with Data Leakage - Oct 8, 2021.
  
  Target leakage and data leakage represent challenging problems in machine learning. Be prepared to recognize and avoid these potentially messy problems.

  Tags: Cross-validation, Data Science, Datasets, Machine Learning, Modeling, Training Data

• The Evolution of Tokenization – Byte Pair Encoding in NLP - Oct 7, 2021.
  
  Though we have SOTA algorithms for tokenization, it's always a good practice to understand the evolution trail and learning how have we reached here. Read this introduction to Byte Pair Encoding.

  Tags: NLP, Python, Tokenization

• How to do “Limitless” Math in Python - Oct 7, 2021.
  
  How to perform arbitrary-precision computation and much more math (and fast too) than what is possible with the built-in math library in Python.

  Tags: Linear Algebra, Mathematics, Probability, Python, Statistics

• Four Different Pipes for R with magrittr - Oct 6, 2021.
  
  The magrittr package supplies the pipe operator (%>%), but it turns out that the package actually contains four pipe operators in total. Let's go into them a bit.

  Tags: Pipeline, R, Tidyverse

• 38 Free Courses on Coursera for Data Science - Oct 6, 2021.
  
  There are so many online resources for learning data science, and a great deal of it can be used at no cost. This collection of free courses hosted by Coursera will help you enhance your data science and machine learning skills, no matter your current level of expertise.

  Tags: Coursera, Data Science Education, Online Education

• My AI Plays Piano for Me - Oct 6, 2021.
  
  Training an RNN with a Combined Loss Function.

  Tags: AI, Music, Neural Networks, Recurrent Neural Networks

• Data science SQL interview questions from top tech firms - Oct 5, 2021.
  
  As a data scientist, there is one thing you really need to understand and know how to handle: data. With SQL being a foundational technical approach for working with data, it should not be surprising that the top tech companies will ask about your SQL skills during an interview. Here, we cover the key concepts tested so you can best prepare for your next data science interview.

  Tags: Amazon, Data Science, Facebook, Google, Interview Questions, SQL

• The Architecture Behind DeepMind’s Model for Near Real Time Weather Forecasts - Oct 5, 2021.
  
  Deep Generative Model of Rain (DGMR) is the newest creation from DeepMind which can predict precipitation in short term intervals.

  Tags: Architecture, DeepMind, Real-time, Weather

• Parallelizing Python Code - Oct 4, 2021.
  
  This article reviews some common options for parallelizing Python code, including process-based parallelism, specialized libraries, ipython parallel, and Ray.

  Tags: Distributed Computing, Parallelism, Programming, Python, Ray

• How to Build Strong Data Science Portfolio as a Beginner - Oct 4, 2021.
  
  After learning the basics of data science, you can start to work on real-world problems. But how do you showcase your work? In this article, we are going to learn a unique way to create a data science portfolio.

  Tags: Beginners, Career Advice, Data Science, Deepnote, GitHub, Kaggle, Portfolio

• Introduction to PyTorch Lightning - Oct 4, 2021.
  
  PyTorch Lightning is a high-level programming layer built on top of PyTorch. It makes building and training models faster, easier, and more reliable.

  Tags: Deep Learning, Neural Networks, PyTorch

• Teaching AI to Classify Time-series Patterns with Synthetic Data - Oct 1, 2021.
  
  How to build and train an AI model to identify various common anomaly patterns in time-series data.

  Tags: AI, Classification, Python, Synthetic Data, Time Series

• How to Auto-Detect the Date/Datetime Columns and Set Their Datatype When Reading a CSV File in Pandas - Oct 1, 2021.
  
  When read_csv( ) reads e.g. “2021-03-04” and “2021-03-04 21:37:01.123” as mere “object” datatypes, often you can simply auto-convert them all at once to true datetime datatypes.

  Tags: Data Processing, Pandas, Python

September:

• How to Determine the Best Fitting Data Distribution Using Python
• Advanced Statistical Concepts in Data Science
• Use These Unique Data Sets to Sharpen Your Data Science Skills
• GitHub Desktop for Data Scientists
• Important Statistics Data Scientists Need to Know
• How To Build A Database Using Python , by Irfan Alghani Khalid
  Implement your database without handling the SQL using the Flask-SQLAlchemy library.

  Tags: Databases, Flask, Python, SQL

• Building a Structured Financial Newsfeed Using Python, SpaCy and Streamlit
• Computer Vision in Agriculture
• Path to Full Stack Data Science , by Jawwad Siddique
  Start your journey toward mastering all aspects of the field of Data Science with this focused list of in-depth self-learning resources. Curated with the beginner in mind, these recommendations will help you learn efficiently, and can also offer existing professionals useful highlights for review or help filling in any gaps in skills.

  Tags: Career Advice, Data Science, Data Science Education, Data Visualization, Mathematics, Python, R, Roadmap

• Zero to RAPIDS in Minutes with NVIDIA GPUs + Saturn Cloud
• Data Analysis Using Scala
• Real-Time Histogram Plots on Unbounded Data
• How To Deal With Imbalanced Classification, Without Re-balancing the Data
• A Breakdown of Deep Learning Frameworks
• 9 Outstanding Reasons to Learn Python for Finance
• GitHub Copilot and the Rise of AI Language Models in Programming Automation
• 20 Machine Learning Projects That Will Get You Hired , by Khushbu Shah
  If you want to break into the machine learning and data science job market, then you will need to demonstrate the proficiency of your skills, especially if you are self-taught through online courses and bootcamps. A project portfolio is a great way to practice your new craft and offer convincing evidence that an employee should hire you over the competition.

  Tags: Career, Machine Learning, Project

• 15 Must-Know Python String Methods
• Data Engineering Technologies 2021
• If You Can Write Functions, You Can Use Dask
• Don’t Touch a Dataset Without Asking These 10 Questions
• How to be a Data Scientist without a STEM degree , by Terence Shin
  Breaking into data science as a professional does require technical skills, a well-honed knack for problem-solving, and a willingness to swim in oceans of data. Maybe you are coming in as a career change or ready to take a new learning path in life--without having previously earned an advanced degree in a STEM field. Follow these tips to find your way into this high-demand and interesting field.

  Tags: Career Advice, Data Science Education, Data Scientist, Project, Python, SQL

• How to Find Weaknesses in your Machine Learning Models , by Michael Berk
  FreaAI: a new method from researchers at IBM.

  Tags: Interpretability, Machine Learning, Modeling, Statistics

• Paradoxes in Data Science
• Introducing TensorFlow Similarity
• Adventures in MLOps with Github Actions, Iterative.ai, Label Studio and NBDEV
• The Machine & Deep Learning Compendium Open Book , by Ori Cohen
  After years in the making, this extensive and comprehensive ebook resource is now available and open for data scientists and ML engineers. Learn from and contribute to this tome of valuable information to support all your work in data science from engineering to strategy to management.

  Tags: Deep Learning, ebook, GitHub, Machine Learning, Open Source

• Easy SQL in Native Python
• Introduction to Automated Machine Learning
• How to get Python PCAP Certification: Roadmap, Resources, Tips For Success, Based On My Experience
• 5 Must Try Awesome Python Data Visualization Libraries
• Speeding up Neural Network Training With Multiple GPUs and Dask
• Data Scientists Without Data Engineering Skills Will Face the Harsh Truth , by Soner Yildirim
  Although the role of the data scientist is still evolving, data remains at its core. Setting the right expectations for what you will do as a data scientist is important, and, to be sure, knowing the tools of data engineering will get yourself ready for the real world.

  Tags: Data Engineering, Data Science Skills, Data Scientist

• An Introduction to Reinforcement Learning with OpenAI Gym, RLlib, and Google Colab
• The Prefect Way to Automate & Orchestrate Data Pipelines
• 3 Most Important Lessons I’ve Learned 3 Years Into My Data Science Career
• Working with Python APIs For Data Science Project
• A Data Science Portfolio That Will Land You The Job , by Natassha Selvaraj
  Landing a data science job is no easy feat, especially during the COVID-19 pandemic. This article provides aspiring data scientists with advice on building a data science portfolio that stands out.

  Tags: Data Science, Jobs, Portfolio

• Text Preprocessing Methods for Deep Learning
• How to Create an AutoML Pipeline Optimization Sandbox
• 8 Deep Learning Project Ideas for Beginners , by Aqsa Zafar
  Have you studied Deep Learning techniques, but never worked on a useful project? Here, we highlight eight deep learning project ideas for beginners that will help you sharpen your skills and boost your resume.

  Tags: Beginners, Deep Learning, Project

• 7 Differences Between a Data Analyst and a Data Scientist , by Zulie Rane
  This article discusses the 7 key differences between data analysts and data scientists with an aim to help potential data analysts/scientists determine which is the right one for them. I touch on day-to-day tasks, skill requirements, typical career progression, and salary and career prospects for both.

  Tags: Career Advice, Data Analysis, Data Analyst, Data Science, Data Scientist

• Top 18 Low-Code and No-Code Machine Learning Platforms , by Yulia Gavrilova
  Machine learning becomes more accessible to companies and individuals when there is less coding involved. Especially if you are just starting your path in ML, then check out these low-code and no-code platforms to help expedite your capabilities in learning and applying AI.

  Tags: AutoML, Data Science Platforms, Low-Code, Machine Learning, No-Code

• How Machine Learning Leverages Linear Algebra to Solve Data Problems
• ebook: Learn Data Science with R – free download
• How to Create Stunning Web Apps for your Data Science Projects , by Murallie Thuwarakesh
  Data scientists do not have to learn HTML, CSS, and JavaScript to build web pages.

  Tags: Apps, Data Science, Python, Streamlit

• Fast AutoML with FLAML + Ray Tune
• Five Key Facts About Wu Dao 2.0: The Largest Transformer Model Ever Built
• Hypothesis Testing Explained , by Angelica Lo Duca
  This brief overview of the concept of Hypothesis Testing covers its classification in parametric and non-parametric tests, and when to use the most popular ones, including means, correlation, and distribution, in the case of one sample and two samples.

  Tags: Hypothesis Testing, Statistics

• 6 Cool Python Libraries That I Came Across Recently
• Build a synthetic data pipeline using Gretel and Apache Airflow
• Best Resources to Learn Natural Language Processing in 2021
• Do You Read Excel Files with Python? There is a 1000x Faster Way , by Nicolas Vandeput
  In this article, I’ll show you five ways to load data in Python. Achieving a speedup of 3 orders of magnitude.

  Tags: Excel, Microsoft, Pandas, Python, Scalability

• Data Science Cheat Sheet 2.0 , by Aaron Wang
  Check out this helpful, 5-page data science cheat sheet to assist with your exam reviews, interview prep, and anything in-between.

  Tags: Cheat Sheet, Data Science

• How is Machine Learning Beneficial in Mobile App Development?

2021 Tutorials, Overviews

2020 Tutorials, Overviews

2019 Tutorials, Overviews

2018 Tutorials, Overviews

2017 Tutorials, Overviews

2016 Tutorials, Overviews