FloydHub has shut down
FloydHub - our ML platform used by thousands of Data Scientists and AI enthusiasts was shut down on August 20, 2021.
Posts
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...
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.
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 -...
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...
Best Machine Learning Books (Updated for 2020)
The list of the best machine learning & deep learning books for 2020.
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...
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.
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.
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
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....
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.
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....
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.
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.
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.
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...
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.
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...
Becoming One With the Data
This article discusses effective ways of handling the data in machine learning projects.
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...
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.
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...
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...
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...
Introduction to Genetic Algorithms
Genetic algorithms are a specific approach to optimization problems that can estimate known solutions and simulate evolutionary behavior in complex systems.
Using Deep Learning and TensorFlow Object Detection API for Corrosion Detection and Localization
While computer vision techniques have been used with limited success for detecting corrosion from images, Deep Learning has opened up whole new possibilities
An introduction to Q-Learning: Reinforcement Learning
Learn about the basic concepts of reinforcement learning and implement a simple RL algorithm called Q-Learning.
How to Build OpenAI's GPT-2: "The AI That Was Too Dangerous to Release"
The Key Insights Behind the Greatest Language Model of all Time
A Beginner’s Guide on Recurrent Neural Networks with PyTorch
Learn the basics of Recurrent Neural Networks and build a simple Language Model with PyTorch
Introduction to K-Means Clustering in Python with scikit-learn
In this article, get a gentle introduction to the world of unsupervised learning and see the mechanics behind the old faithful K-Means algorithm.
A Gentle Introduction to Text Summarization in Machine Learning
Text summarization is a common problem in the fields of machine learning and natural language processing (NLP). In this article, we'll explore how to create...
Introduction to Anomaly Detection in Python
Learn what anomalies are and several approaches to detect them along with a case study.
Meta-Reinforcement Learning
The general trend in machine learning research is to stop fine-tuning models, and instead use a meta-learning algorithm that automatically finds the best architecture and...
Ten trends in Deep learning NLP
Let's uncover the Top 10 NLP trends of 2019.
Best Deep Learning Courses: Updated for 2019
The list of the best machine learning & deep learning courses and MOOCs for 2019.
Best Deep Learning Books: Updated for 2019-2020
The list of the best machine learning & deep learning books for 2019.
Controlling a 2D Robotic Arm with Deep Reinforcement Learning
Learn how to control a robotic arm using deep reinforcement learning techniques.
Recommending Similar Fashion Images with Deep Learning
Explore how deep learning is changing the fashion industry by training your own visual recommendation model for similar fashion images using TensorFlow and FloydHub
Building a Toy Self-Driving Car: Part One
Learn the history and technology of autonomous cars in this Part 1 of a series on building a self-driving toy car with Raspberry Pi, Keras,...
On Building an Instagram Street Art Dataset and Detection Model
Build your own deep learning dataset and detection model using public Instagram photos of #streetart.
Haggis, Not Haggis: How to build a haggis detection app with TensorFlow, Keras, and FloydHub for Burns Night
Use TensorFlow to build your own haggis-hunting app for Burns Night! The Scottish quest for the mythical wild haggis just got easier with deep learning....
Inverting Facial Recognition Models
Can we teach a neural net to convert face embedding vectors back to images?
Using NLP to Automate Customer Support, Part Two
Let's build an NLP model that can help out your customer support agents by suggesting previously-asked, similar questions.
Improving Access to Sexual Health Education in Kenya with Artificial Intelligence
Irving Amukasa built an AI chatbot to answer questions about reproductive health for young people in Kenya. Learn more in this #humansofml interview.
Exploring DNA with Deep Learning
Neural networks are transforming the way we study DNA and population genetics. Learn more about deep learning at Bayer Crop Science from Lex Flagel in...
Teaching Humans How to Teach Computers
Resistance is futile — Siraj Raval will teach artificial intelligence (AI) literacy to every single person in this galactic quadrant. Learn more about Siraj's background...
Using Sentence Embeddings to Automate Customer Support, Part One
Most of your customer support questions have already been asked. Learn how to use sentence embeddings to automate your customer support with AI.
Spinning Up a Pong AI With Deep Reinforcement Learning
Dive into deep reinforcement learning by training a model to play the classic 1970s video game Pong — using Keras, FloydHub, and OpenAI's "Spinning Up."...
Reading Minds with Deep Learning
Explore the latest trends in Brain-Computer Interfaces - and train a deep learning model to predict what people are doing from fluctuations in their brain...
Generating Classical Music with Neural Networks
Christine McLeavey Payne may have finally cured songwriter's block. Her recent project Clara is a long short-term memory (LSTM) neural network that composes piano and...
Recognize relatives using deep learning
Building a cousin image classification app using a convolutional neural net for your Thanksgiving family reunion using fast.ai and FloydHub.
DeOldify: Colorizing and Restoring Old Images and Videos with Deep Learning
Jason Antic's DeOldify deep learning project not only colorizes images but also restores them with stunning results. Learn more about his approach in this FloydHub...
How to become a FloydHub A.I. Writer
TLDR: Apply now, write insanely great tutorials, and get paid in GPU credit (or 💵)
Found in translation: Building a language translator from scratch with deep learning
Build an English-French language translator from scratch using PyTorch.
How to code The Transformer in PyTorch
Learn how to code a transformer model in PyTorch with an English-to-French language translation task
Practical Guide to Hyperparameters Optimization for Deep Learning Models
Learn techniques for identifying the best hyperparameters for your deep learning projects, including code samples that you can use to get started on FloydHub.
Counting the Crowd at Shake Shack with Deep Learning
The FloydHub #humansofml interview with Dimitri Roche - a software engineer who built a Shake Shack crowd-counting CoreML app using deep learning and FloydHub
Asking questions to images with deep learning: a visual-question-answering tutorial
In this deep learning tutorial, we'll build Visual Question Answering (VQA) model that allows people to ask open-ended, common sense questions about the visual world....
Ten Techniques Learned From fast.ai
Right now, Jeremy Howard – the co-founder of fast.ai – currently holds the 105th highest score for the plant seedling classification contest on Kaggle, but...
Exploring Computational Creativity with Neural Networks
The FloydHub #humansofml interview with Kalai Ramea - a researcher at Palo Alto Research Center where she works on fundamental machine learning research involving computer...
Revolutionizing the Fashion Industry with Artificial Intelligence
The FloydHub #HumansOfML Interview with Leanne Luce -- designer, technologist, and author of the upcoming book "Artificial Intelligence for Fashion."
5 advanced features that save you time on FloydHub
FloydHub has a lot of features that accelerate various stages of your ML workflow. In this post we are sharing the 5 most useful features...
Generating Commencement Speeches With Markov Chains
Generate your own commencement speeches using Markov chains in Python on FloydHub.
Automate FloydHub with Celery
Jelle Hoffman from Ubidots shows how he used Celery to automate their FloydHub API management
Workspaces on FloydHub
Meet Workspaces 👋- a new cloud IDE for deep learning, powered by FloydHub GPUs
Metrics on FloydHub
Learn how FloydHub's new metrics features give you real-time insights into training performance and system resource utilization for optimal deep learning model development.
FloydHub for Teams
We're launching a Teams plan on FloydHub today. You can now have a secure, centralized hub for your entire data science team's model development, training,...
Teaching My Robot With TensorFlow
If you're like me, then you'd do pretty much anything to have your own R2-D2 or BB-8 robotic buddy. Just imagine the adorable adventures you'd...
Turning Design Mockups Into Code With Deep Learning
Within three years deep learning will change front-end development. It will increase prototyping speed and lower the barrier for building software.
Benchmarking FloydHub instances
This post compares all the CPU and GPU instances offered by FloydHub, so that you can choose the right instance type for your training job....
Checkpointing Tutorial for TensorFlow, Keras, and PyTorch
Ready to build, train, and deploy AI? Get started with FloydHub's collaborative AI platform for free Try FloydHub for free [https://www.floydhub.com/?utm_source=blog&utm_medium=banner-checkpointing-s...
Creating Datasets from Public URLs
We're trying to make it easier to discover and use interesting datasets on FloydHub. To that end, we just released an improved file-viewer to help...
Generating Six-Pack Abs With TensorFlow pix2pix
Visualizing results can be a powerful form of motivation and preparation. However, in the fitness domain, it can often be difficult to clearly see this...
Colorizing B&W Photos with Neural Networks
I’ll show you how to build your own colorization neural net in three steps. The first section breaks down the core logic. We’ll build a...
Building Your First ConvNet
Learn how to build your first ConvNet (Convolutional Neural Networks) to classify dogs and cats.
Restart Jupyter Notebook Workflow
We snuck in a new feature that should make your Jupyter notebook workflow on FloydHub oh-so-much easier - the restart button. Now you can spin...
Getting Started with Deep Learning on FloydHub
This post is aimed at helping new users (especially the ones who are starting out & cannot afford Andrej Karpathy’s rig [https://twitter.com/karpathy/status/648256662554341377]) setup an on-the-go...
Coding the History of Deep Learning
There are six snippets of code that made deep learning what it is today. This article covers the inventors and the background to their breakthroughs....
Should I buy my own GPUs for Deep Learning?
Deep learning algorithms involve huge amounts of matrix multiplications and other operations which can be massively parallelized. GPUs usually consist of thousands of cores which...
My First Weekend of Deep Learning
The current wave of deep learning took off five years ago. Exponential progress in computing power followed by a few success stories created the hype....
Hello, README files
We're introducing a new feature to help you explore projects and share your work on FloydHub that you may already recognize - README files. Starting...
Tensorboard on FloydHub
Want to run Tensorboard on FloydHub?! No problem! We make it easy.