Inspiration - FloydHub Blog

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

Deep Learning

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, and FloydHub GPUs.

Deep Learning

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.

Deep Learning

Inverting Facial Recognition Models

Can we teach a neural net to convert face embedding vectors back to images?

Humans of Machine Learning

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.

Humans of Machine Learning

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 this #humansofml interview.

Community

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.

Deep Learning Featured

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."

Deep Learning

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 voltage readings.

Humans of Machine Learning

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 chamber music. Just give Clara a taste of your magnum-opus-in-progress, and Clara will figure out what you should play next.

Inspiration

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.

Humans of Machine Learning Featured

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 #humansofml interview.

Deep Learning

Found in translation: Building a language translator from scratch with deep learning

Build an English-French language translator from scratch using PyTorch.

Inspiration

Generating Commencement Speeches With Markov Chains

Generate your own commencement speeches using Markov chains in Python on FloydHub.

Inspiration

Automate FloydHub with Celery

Jelle Hoffman from Ubidots shows how he used Celery to automate their FloydHub API management

Inspiration Featured

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 have together! I'm delighted to report that the Anki Cozmo [https://www.anki.com/en-us/cozmo] is

Deep Learning Featured

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.

Inspiration

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 future outcome. Can we use deep learning to bring people closer to their individual fitness goals by helping them visualize their future results? This was