Data Science

Data Science | News, how-tos, features, reviews, and videos

teamwork / colleagues / collaboration / data / charts / analysis / planning / strategy
7 artificial intelligence

maze lost question direction wayward

Semi-supervised learning explained

Using a machine learning model’s own predictions on unlabeled data to add to the labeled data set sometimes improves accuracy, but not always

neural network

Deep learning frameworks: PyTorch vs. TensorFlow

If you actually need a deep learning model, PyTorch and TensorFlow are both good choices

Illustration of head made out of gears with 2 hands holding it with cloud background

Automated machine learning or AutoML explained

AutoML frameworks and services eliminate the need for skilled data scientists to build machine learning and deep learning models

Oragami unicorn

Stop searching for that data scientist unicorn

Instead, focus on hiring the technical skills needed to build the team, and the soft skills needed to work on the team

data scientist woman at virtual monitor user interface tools for data science by metamorworks getty

Applying devops in data science and machine learning

Having data scientists collaborate with devops and engineers leads to better business outcomes, but understanding their different requirements is key

A human profile containing digital wireframe of technology connections.

The best machine learning and deep learning libraries

TensorFlow, Spark MLlib, Scikit-learn, PyTorch, MXNet, and Keras shine for building and training machine learning and deep learning models

Clash of fists in silhouette

Julia vs. Python: Which is best for data science?

Python has turned into a data science and machine learning mainstay, while Julia was built from the ground up to do the job

abstract binary vortex matrix motion digtial transformation disruption  by simon carter peter crowt

TensorFlow 2 review: Easier machine learning

Now more platform than toolkit, TensorFlow has made strides in everything from ease of use to distributed training and deployment

blank tag isolated on white 95754104

Supervised learning explained

Supervised learning turns labeled training data into a tuned predictive model

blockchain network machine learning neural network

What is TensorFlow? The machine learning library explained

TensorFlow is a Python-friendly open source library for numerical computation that makes machine learning faster and easier

watering a flower 115579466

What’s new in TensorFlow 2.0

Google’s TensorFlow 2.0 is now available in beta, with a focus on improving performance, ease, compatibility, and continuity

happy confetti celebrate victory proud winner ambreen hasan 346960 unsplash

The best new features in Python 3.8

From a powerful new assignment syntax to under-the-hood overhauls, Python 3.8 steps toward a more modern Python codebase

Go opening by  2400x1600

Reinforcement learning explained

Reinforcement learning uses rewards and penalties to teach computers how to play games and robots how to perform tasks independently

machine learning

Machine learning explained

Able to learn from data, machine learning algorithms can solve problems that are too complex to solve with conventional programming

Exploding binary numbers

Machine learning algorithms explained

Machine learning uses algorithms to turn a data set into a model. Which algorithm works best depends on the problem

Jupiter and its four planet-size moons, in their relative positions but not to scale; 1998/Voyager 1

What is Jupyter Notebook? Data analysis made easier

Jupyter Notebook combines live code, graphics, visualizations, and text in shareable notebooks that run in a web browser


Mozilla brings Python data science to the browser

Pyodide project uses Emscripten and WebAssembly to run Python and its data science libraries in any major browser

gears iot

Review: Google Cloud AutoML is truly automated machine learning

Google’s AutoML lets you create customized deep learning models without any knowledge of data science or programming

Load More