DataScience Digest — Issue #18

Dmitry Spodarets

Hi all! We’re in the midst of summer… So, if you’re going to hit the beach in Odessa around July 5, I invite you to mix business with pleasure, to take part in the upcoming hosted by Odessa’s team. Bear in mind that the digest has a , as well as social media pages on , , and . There you’ll find the links to useful and insightful content in the AI and data space. Make sure you join in! And for now, check out the latest of our digest.

An easy approach to data pipelining using PySpark and doing distributed deep learning with Keras.

This post offers a review of a large number of interesting applications of GANs to help you develop an intuition for the types of problems where GANs can be used and useful. It’s not an exhaustive list, but it does contain many example uses of GANs that have been in the media.

In this article, you will learn how to pull stock prices from online API and perform predictions using Recurrent Neural Network & Long Short Term Memory (LSTM) with TensorFlow.js framework.

Initialization can have a significant impact on convergence in training deep neural networks. Simple initialization schemes can accelerate training, but they require care to avoid common pitfalls. In this post, we’ll explain how to initialize neural network parameters effectively.

A long-awaited update of the data science skill portfolio

In this article, you will learn about OpenCV library and basic functions: Reading, Writing and Displaying Images, Changing Color Spaces, Resizing Images, Image Rotation, Image Translation, Simple Image Thresholding, Adaptive Thresholding, Image Segmentation (Watershed Algorithm), Bitwise Operations, Edge Detection, Image Filtering, Image Contours, Scale Invariant Feature Transform (SIFT), Speeded-Up Robust Features (SURF), Feature Matching, Face Detection.

This article will help you to take your first steps into the world of deep reinforcement learning. We’ll use one of the most popular algorithms in RL, deep Q-learning, to understand how deep RL works. We will implement all learnt in an awesome case study using Python.

This post offers a detailed roadmap to how you can learn Deep Learning well enough to get a Deep Learning internship as well as a full-time job within 6 months. This post is practical, result oriented and follows a top-down approach. It is aimed for beginners strapped for time, as well as for intermediate practitioners.

In this article, the author demonstrates a few areas where signals or time series are vital, after which he briefly reviews classical approaches and moves on to his experience with applying deep learning for biosignal analysis in Mawi Solutions and for algorithmic trading.

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.

In this article, you will learn the basic steps of text preprocessing. These steps are needed for transferring text from human language to machine-readable format for further processing. You will also learn about text preprocessing tools.

A useful collection of resources to catch up on the latest trends in natural language processing. In addition to selected research papers, this article includes links to introductory posts, recommended blogs, online courses, and books.

: – Artificial Intelligence – Big Data Analytics – Data Mining – Data Science – Data Visualization – Deep Learning – Machine Learning – etc…

This repository sums up all the important stuff covered in Stanford’s CS 221 Artificial Intelligence course and includes: – Cheatsheets for each field of artificial intelligence. – All elements of the above combined in the ultimate compilation of concepts to have at hand all the time.

Video recordings of presentations from Deep Learning Boot Camp, which was held from 28 to 31 May in Berkeley.

For those who weren’t at ICLR and want to browse the papers that were presented there, this is for you; it lets you check out many of the posters from the official ICLR poster session. In the future, founders plan to publish poster sessions from other top machine learning conferences too.

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

A curated list of applied machine learning and data science notebooks and libraries across different industries.

This open access book presents the first comprehensive overview of general methods in Automated Machine Learning (AutoML), collects descriptions of existing systems based on these methods, and discusses the first series of international challenges of AutoML systems.

Looking forward to ODS.ai taking place July 5in Odessa. Join the first informal meetup community on in the Odessa region. Lots of networking and heated discussion on the upcoming conference are guaranteed. The participation is free, but is required.

read original article at https://medium.com/datasciencedigest/datascience-digest-issue-18-49da3b4c2b10?source=rss——artificial_intelligence-5

Share
Do NOT follow this link or you will be banned from the site!