Aroma: Using machine learning for code recommendation

In this article, you will learn about Aroma - a code-to-code search and recommendation tool that uses machine learning (ML) to simplify gaining insights from big codebases.

Link: http://bit.ly/2La3T6u

An End-to-End Project on Time Series Analysis and Forecasting with Python

This article explains how to use time series for non-stationary data, like economic, weather, stock price, and retail sales. You will learn different approaches for forecasting retail sales time series.

Link: http://bit.ly/2LaZT5F

AutoML for Data Augmentation

In this article, you will learn about DeepAugment — an AutoML tool focusing on data augmentation. It utilizes Bayesian optimization for discovering data augmentation strategies tailored to your image dataset.

Link: http://bit.ly/2W9H9o5

Using Reinforcement Learning to Design a Better Rocket Engine

In this article, you will learn how to use reinforcement learning to develop innovative solutions in rocket engine development. You will see how ML techniques can be applied to the manufacturing industry and learn more about the role of the Machine Learning Product Manager.

Link: http://bit.ly/2VdABIQ

Top 5 Interesting Applications of GANs for Every Machine Learning Enthusiast!

In this article, you will learn about five intriguing applications of GANs that are prevalent in the industry: GANs for Image Editing, Using GANs for Security, Generating Data using GANs, GANs for Attention Prediction, GANs for 3D Object Generation. Links to research papers for each GAN application are included.

Link: http://bit.ly/2GQgsyr

A Recommendation Model with PyTorch

This article will outline the idea of Probabilistic Matrix Factorization and its use in recommendation systems on PyTorch.

Link: http://bit.ly/2GZcIuf

CariGANs: Unpaired Photo-to-Caricature Translation

Facial caricature is an art form of drawing faces in an exaggerated way to convey humor or sarcasm. In this paper, we propose the first Generative Adversarial Network (GAN) for unpaired photo-to-caricature translation, which we call "CariGANs". It explicitly models geometric exaggeration and appearance stylization using two components: CariGeoGAN, which only models the geometry-to-geometry transformation from face photos to caricatures, and CariStyGAN, which transfers the style appearance from caricatures to face photos without any geometry deformation. In this way, a difficult cross-domain translation problem is decoupled into two easier tasks. The perceptual study shows that caricatures generated by our CariGANs are closer to the hand-drawn ones, and at the same time better persevere the identity, compared to state-of-the-art methods. Moreover, our CariGANs allow users to control the shape exaggeration degree and change the color/texture style by tuning the parameters or giving an example caricature.

Link: http://bit.ly/2H1wvt1

Bayes Theorem in One Picture - http://bit.ly/2H1LfrW

MRNet Dataset

The MRNet dataset consists of 1,370 knee MRI exams performed at Stanford University Medical Center. The dataset contains 1,104 (80.6%) abnormal exams, with 319 (23.3%) ACL tears and 508 (37.1%) meniscal tears; labels were obtained through manual extraction from clinical reports.

Link: http://bit.ly/2H3YwAg

Fast Neural Style Transfer in PyTorch

PyTorch implementation of Fast Neural Style Transfer.

Link: http://bit.ly/2H0Ob8k

Google Coral Edge TPU Board Vs NVIDIA Jetson Nano Dev board 

This article compares the hardware of the two dev kits which can be used as a Single board computer (SBC), but not an Edge TPU USB stick.

Link: http://bit.ly/2HagSj0

Easy Image Classification with TensorFlow 2.0

This article will introduce you to TensorFlow 2.0 by exploring how to apply its high-level APIs in classic image classification.

Link: http://bit.ly/2VqaIFM

Dear readers!

As you might already know, we're working tirelessly to create and regularly update the collection of exciting and useful content on ML, DL, NLP, CV, etc. — Data Science Digest. Hope you love it all so far.

Anyway, just letting you know that the digest is now available on:
- Facebook: http://bit.ly/2HdrL3I
- Twitter: http://bit.ly/2HcBA22
- LinkedIn: http://bit.ly/2HjAbXA
- Telegram: http://bit.ly/2H9XEKA

We also run newsletter updates you can always subscribe to here: http://bit.ly/2HcdaFP.

You're welcome to join to never miss out on our next digest update. Enjoy!

Your Data Science Digest team!

Generating Images with Autoencoders

This tutorial will introduce you to unsupervised and self-supervised learning using neural networks for image generation, image augmentation, and image blending. The first part is focused on a specific type of autoencoder called a variational autoencoder.

Link: http://bit.ly/2HikL5x

Advanced Keras — Constructing Complex Custom Losses and Metrics

In this tutorial, you will learn about a simple trick that will help you construct custom loss functions in Keras which can receive arguments other than ytrue and ypred.

Link: http://bit.ly/2VtrzaI

Benchmarking Edge Computing

We will compare the following platforms: the Coral Dev Board, the NVIDIA Jetson Nano, the Coral USB Accelerator with a Raspberry Pi, the original Movidus Neural Compute Stick with a Raspberry Pi, and the second generation Intel Neural Compute Stick 2 again with a Raspberry Pi. Finally, just to add a yardstick, we’ll also run the same models on my Apple MacBook Pro (2016), which has a quad-core 2.9 GHz Intel Core i7, and a vanilla Raspberry Pi 3, Model B+ without any acceleration.

http://bit.ly/2HtRUf0

Getting started with the NVIDIA Jetson Nano

In this tutorial, you will learn how to get started with your NVIDIA Jetson Nano, including:
- First boot
- Installing system packages and prerequisites
- Configuring your Python development environment
- Installing Keras and TensorFlow on the Jetson Nano
- Changing the default camera
- Classification and object detection with the Jetson Nano

http://bit.ly/2VCmZqs

Object detection and image classification with Google Coral USB Accelerator

In this tutorial, you will learn how to get started with Google Coral USB Accelerator, including:
- Image classification with the Coral USB Accelerator
- Image classification in video with the Google Coral Accelerator
- Object detection with the Google Coral Accelerator
- Object detection in video with the Coral USB Accelerator

http://bit.ly/2VJVxY7

TensorFlow Graphics

TensorFlow Graphics is one of the latest additions to TensorFlow, which is expected to enable research in the intersection of deep learning and computer graphics.

http://bit.ly/2VGWtfI

Github repository: http://bit.ly/2VKNElc

The Best Machine Learning Resources

This article is an addendum to the series «Machine Learning for Humans» a guide for getting up-to-speed on machine learning concepts in 2-3 hours.

http://bit.ly/2HDWkzK

GraphPipe

GraphPipe is a protocol and collection of software designed to simplify machine learning model deployment and to decouple it from framework-specific model implementations.

http://bit.ly/2HCCVzh