Heartbeat Collections

A catalogue of Heartbeat posts that dive into the most recent and most popular research efforts across the machine/deep learning landscape

Image Source

Machine and Deep Learning Research

The machine learning world moves quickly. It’s nearly impossible to keep up with all the latest amazing research that’s happening all around the globe.

From architecture optimization to task-based research and beyond, there are so many incredible efforts being undertaken to push the ML landscape into new, exciting frontiers.

And while we can’t possibly cover every new development, we have a number of excellent Heartbeat articles that review, summarize, and otherwise explore current research trends. This list should provide a good starting point for diving into some of the core ML research out there.

A 2019 Guide to Semantic Segmentation

A review of state-of-the-art approaches to semantic segmentation.

— by Derrick Mwiti

A 2019 Guide to Semantic Segmentation

Capsule Networks: A new and attractive AI architecture

Learn what capsule networks are and why they’re good for handling object features like pose, deformation, velocity, albedo, hue, texture, and more.

— by Ayyüce Kızrak

Capsule Networks: A new and attractive AI architecture🚨

A 2019 Guide for Automatic Speech Recognition

Popular and recent approaches to processing and identifying human voices with deep learning.

— by Derrick Mwiti

A 2019 Guide for Automatic Speech Recognition

A 2019 Guide to Object Detection

Common model architectures and a few new approaches to object detection, a computer vision task in machine learning.

— by Derrick Mwiti

A 2019 Guide to Object Detection

A 2019 Guide to Speech Synthesis with Deep Learning

Popular and current deep learning approaches to speech synthesis.

— by Derrick Mwiti

A 2019 Guide to Speech Synthesis with Deep Learning

The Mobile Neural Network Lottery

Exploring a new method for optimizing machine learning models for mobile devices.

— by Vincent Fortuin

The Mobile Neural Network Lottery

A 2019 Guide to Deep Learning-Based Image Compression

Reviewing popular and recent approaches to image compression via deep learning.

— by Derrick Mwiti

A 2019 Guide to Deep Learning-Based Image Compression

ActiveStereoNet: The first deep learning solution for active stereo systems

Review and commentary centered on ActiveStereoNet, an end-to-end self-supervised learning for active stereo systems.

— by Erez Posner

ActiveStereoNet: The first deep learning solution for active stereo systems

A 2019 Guide to Human Pose Estimation

Examining popular and current approaches to the computer vision task of human pose estimation.

— by Derrick Mwiti

A 2019 Guide to Human Pose Estimation

StyleGAN: Use machine learning to generate and customize realistic images

Learn the foundational components of StyleGANs, a popular generative adversarial deep learning architecture.

— by Jamshed Khan

StyleGANs: Use machine learning to generate and customize realistic images

Research Guide for Transformers

A deep dive into popular and current deep learning-based approaches to neural machine translation and other NLP tasks with Transformers.

— by Derrick Mwiti

Research Guide for Transformers

Deep Learning for Image Segmentation: U-Net Architecture

Exploring the u-net deep learning architecture for segmentation.

— by Ayyüce Kızrak

Deep Learning for Image Segmentation: U-Net Architecture

Guide to Image Inpainting: Using machine learning to edit and correct defects in photos

A discussion of image inpainting and a review of popular and current approaches.

— by Jamshed Khan

Guide to Image Inpainting: Using machine learning to edit and correct defects in photos

Anatomy of a High-Performance Convolution

Perhaps not traditional “research”, but an excellent exploration of ways to optimize neural network operations.

— by Manas Sahni

Anatomy of a High-Performance Convolution

Research Guide for Video Frame Interpolation with Deep Learning

In this article, we’ll look at deep learning papers aimed at synthesizing video frames within an existing video.

— by Derrick Mwiti

Research Guide for Video Frame Interpolation with Deep Learning

Research Guide for Neural Architecture Search

Reviewing popular and current approaches to Neural Architecture Search, which seeks to automate the process of designing neural networks.

— by Derrick Mwiti

Research Guide for Neural Architecture Search

Research Guide for Depth Estimation with Deep Learning

A deep dive into popular and current deep learning-based approaches to estimating depth from 2D images.

— by Derrick Mwiti

Research Guide for Depth Estimation with Deep Learning

Research Guide: Advanced Loss Functions for Machine Learning Models

A deep dive into popular and recent advanced loss functions designed to improve a variety of ML models.

— by Derrick Mwiti

Research Guide: Advanced Loss Functions for Machine Learning Models

Editor’s Note: Heartbeat is a contributor-driven online publication and community dedicated to exploring the emerging intersection of mobile app development and machine learning. We’re committed to supporting and inspiring developers and engineers from all walks of life.

Editorially independent, Heartbeat is sponsored and published by Fritz AI, the machine learning platform that helps developers teach devices to see, hear, sense, and think. We pay our contributors, and we don’t sell ads.

If you’d like to contribute, head on over to our call for contributors. You can also sign up to receive our weekly newsletters (Deep Learning Weekly and Heartbeat), join us on Slack, and follow Fritz AI on Twitter for all the latest in mobile machine learning.