Product Featured

FloydHub has shut down

FloydHub - our ML platform used by thousands of Data Scientists and AI enthusiasts was shut down on August 20, 2021.

Deep Learning

NLP Datasets: How good is your deep learning model?

With the rapid advance in NLP models we have outpaced out ability to measure just how good they are at human level language tasks. We need better NLP datasets now more than ever to both evaluate how good these models are and to be able to tweak them for out own business domains.

Humans of Machine Learning

The Future of AI is Open

This Humans of ML interview with Han Xiao covers the ethics of AI, open-source entrepreneurship, how writing made Han a better coder, and more.

Data Science

FloydHub Cloud Setup Challenge: Jupyter + TensorFlow in 44 seconds [WR]

Is it possible for data science beginners to get up and running in under 90 seconds? FloydHub’s team takes on the setup cloud challenge - and walks away with the trophy. (For now!)

Humans of Machine Learning

Talking ML and Cloud Transformation at AI-First Companies with @searchguy, aka Antonio Gulli

This Humans of Machine Learning interview has us sitting down with Searchguy, aka Antonio Gulli, who’s been a pioneer in the world of data science for 20+ years now, to talk transformation, opportunity, and mentorship, among other topics.

Machine Learning

Best Machine Learning Books (Updated for 2020)

The list of the best machine learning & deep learning books for 2020.

Machine Learning Platform Featured

AWS Cost Optimization for ML Infrastructure - EC2 spend

[Series] Based on his deep experience, FloydHub CTO Naren discusses how should companies think about & setup their ML infrastructure. This article focuses on AWS EC2 machines.

NLP Featured

Tokenizers: How machines read

We will cover often-overlooked concepts vital to NLP, such as Byte Pair Encoding, and discuss how understanding them leads to better models.

Humans of Machine Learning Featured

Emil’s Story as a Self-Taught AI Researcher

This Humans of Machine Learning interview covers Emil Wallner and his hero’s journey, self-taught approach to education, experience with AI, and path to Google.

Deep Learning Featured

Distilling knowledge from Neural Networks to build smaller and faster models

This article discusses GPT-2 and BERT models, as well using knowledge distillation to create highly accurate models with fewer parameters than their teachers

Data Science

Naïve Bayes for Machine Learning – From Zero to Hero

Bayes’ Theorem is about more than just conditional probability, and Naive Bayes is a flavor of the theorem which adds to its complexity and usefulness.

Data Science

A Pirate's Guide to Accuracy, Precision, Recall, and Other Scores

Once you've built your classifier, you need to evaluate its effectiveness with metrics like accuracy, precision, recall, F1-Score, and ROC curve.

Deep Learning

Introduction to Adversarial Machine Learning

Machine learning advancements lead to new ways to train models, as well as deceive them. This article discusses ways to train and defend against attacks.

Deep Learning

Training Neural Nets: a Hacker’s Perspective

This deep dive is all about neural networks - training them using best practices, debugging them and maximizing their performance using cutting edge research.

Deep Learning

Attention Mechanism

What is Attention, and why is it used in state-of-the-art models? This article discusses the types of Attention and walks you through their implementations.

Data Science

Multiprocessing vs. Threading in Python: What Every Data Scientist Needs to Know

This deep dive on Python parallelization libraries - multiprocessing and threading - will explain which to use when for different data scientist problem sets.

Deep Learning

When Not to Choose the Best NLP Model

The world of NLP already contains an assortment of pre-trained models and techniques. This article discusses how to best discern which model will work for your goals.

Deep Learning

N-Shot Learning: Learning More with Less Data

Is it possible to use machine learning with small data? Yes, it is! Here's N-Shot Learning.

Deep Learning

Gated Recurrent Unit (GRU) With PyTorch

The Gated Recurrent Unit (GRU) is the newer version of the more popular LSTM. Let's unveil this network and explore the differences between these 2 siblings.

Deep Learning

Becoming One With the Data

This article discusses effective ways of handling the data in machine learning projects.

Data Science

DIY Data: Web Scraping with Python and BeautifulSoup

Getting sufficient clean, reliable data is one of the hardest parts of data science. Web scraping automates the process of visiting web pages, downloading the data, and cleaning the results. With this technique, we can create new datasets from a large compendium of web pages.

Deep Learning

How to plan and execute your ML and DL projects

This article gives the readers a checklist to structure their machine learning (applies to deep ones too) projects in effective ways.

Data Science

Statistics for Data Science

The article elucidates the importance of statistics in the field of data science, wherein "Statistics" is imagined as a friend to a data scientist and their friendship is unraveled.

Deep Learning Featured

Generative Adversarial Networks - The Story So Far

Generative adversarial networks (GANs) have been the go-to state of the art algorithm to image generation in the last few years. In this article, you will learn about the most significant breakthroughs in this field, including BigGAN, StyleGAN, and many more.

Deep Learning

Long Short-Term Memory: From Zero to Hero with PyTorch

Long Short-Term Memory (LSTM) Networks have been widely used to solve various sequential tasks. Let's find out how these networks work and how we can implement them.