Collaborating Authors

Neural Networks

IEEE ICRA 2021 Awards (with videos and papers)


Did you have the chance to attend the 2021 International Conference on Robotics and Automation (ICRA 2021)? Here we bring you the papers that received an award this year in case you missed them. "An essential and challenging use case solved and evaluated convincingly. This work brings to light the artisanal field that can gain a lot in terms of safety and worker's health preservation through the use of collaborative robots. Simulation is used to design advanced control architectures, including virtual walls around the cutting-tool as well as adaptive damping that would account for the operator know-how and level of expertise."

Feed Forward Neural Network


A Feed Forward Neural Network is commonly seen in its simplest form as a single layer perceptron. In this model, a series of inputs enter the layer and are multiplied by the weights. Each value is then added together to get a sum of the weighted input values. If the sum of the values is above a specific threshold, usually set at zero, the value produced is often 1, whereas if the sum falls below the threshold, the output value is -1. The single layer perceptron is an important model of feed forward neural networks and is often used in classification tasks. Furthermore, single layer perceptrons can incorporate aspects of machine learning.

Artificial Neural Patches


This article describes what neural patches and patch systems are, their advantage over tradition neural network design, and why we're looking for people to train interesting artificial neural patches for image classification. It goes over the steps to train such patches using a simple Windows tool, how to test them in the wild on mobile devices (iOS and Android) and submit them for publication review. In 2006 researchers used fMRI (functional magnetic resonance imaging) and electrical recordings of individual nerve cells to find regions of the inferior temporal lobe that become active when macaque monkeys observe another monkey's face. They found that some nerve regions are triggered only when a face is identified. And those trigger other regions which show sensitivity to only specific orientations of the face, or to specific feature exaggerations. Such regions of a neural network that are conditionally activated in the presence of certain coarse features, and then extract more finer features, are referred to as Neural Patches.

Open Source Projects for Machine Learning Enthusiasts


Open source refers to something people can modify and share because they are accessible to everyone. You can use the work in new ways, integrate it into a larger project, or find a new work based on the original. Open source promotes the free exchange of ideas within a community to build creative and technological innovations or ideas. It helps you to write cleaner code. That can be of any choice.

Offline Data Augmentation for multiple images in Python


Can you increase the number of images in any dataset? Machine learning, Deep learning, Artificial intelligence all require large amounts of data. However, data is not always available in every case. The programmer needs to work with the small amount of data available. Hence the use of data augmentation came into the picture.

The Modern Mathematics of Deep Learning


We describe the new field of mathematical analysis of deep learning. This field emerged around a list of research questions that were not answered within the classical framework of learning theory. These questions concern: the outstanding generalization power of overparametrized neural networks, the role of depth in deep architectures, the apparent absence of the curse of dimensionality, the surprisingly successful optimization performance despite the non-convexity of the problem, understanding what features are learned, why deep architectures perform exceptionally well in physical problems, and which fine aspects of an architecture affect the behavior of a learning task in which way. We present an overview of modern approaches that yield partial answers to these questions. For selected approaches, we describe the main ideas in more detail.

8 Alternatives to TensorFlow Serving


TensorFlow Serving is an easy-to-deploy, flexible and high performing serving system for machine learning models built for production environments. It allows easy deployment of algorithms and experiments while allowing developers to keep the same server architecture and APIs. TensorFlow Serving provides seamless integration with TensorFlow models, and can also be easily extended to other models and data. Open-source platform Cortex makes execution of real-time inference at scale seamless. It is designed to deploy trained machine learning models directly as a web service in production.

Advanced AI eBooks Bundle by Morgan Claypool


If the potential and possibility of artificial intelligence has always fascinated you, get ready for the perfect bundle to fill the next few weeks with! Humble Bundle teamed up with Morgan & Claypool to bring you insights into AI and its applications into autonomous vehicles, conversational systems, and more! Pick up this bundle and you'll enjoy discovering eBooks like Why AI/Data Science Projects Fail: How to Avoid Project Pitfalls, Deep Learning Systems: Algorithms, Compilers, and Processors for Large-Scale Production, and Conversational AI: Dialogue Systems, Conversational Agents, and Chatbots. Your purchase of this bundle helps support a charity of your choice. This bundle launched on June 14 at 11:00 am PST and lasts through July 05, 2021.

A Short Discussion on Bias in Machine Learning


In the last decade, advances in data science and engineering have made possible the development of various data products across industry. Problems that not so long ago were treated as very difficult for machines to tackle are now solved (to some extent) and available at large scale capacities. These include many perceptual-like tasks in computer vision, speech recognition, and natural language processing (NLP). Nowadays, we can contract large-scale deep learning-based vision systems that can recognize and verify faces on images and videos. In the same way, we can take advantage of large-scaled language models to build conversational bots, analyze large bodies of text to find common patterns, or use translation systems that can work on nearly any modern language.

Detection of ripe flowers of the Alstroemeria genus Morado


The authors of this blog are Stan Zwinkels & Ted de Vries Lentsch. This blog aims to present our attempt to create a detection algorithm for detecting ripe flowers of the Alstroemeria genus Morado. Throughout this blog, we explain our process to create a dataset and detection model that achieves an F1 score of more than 0.75. This blog is part of the course Seminar Computer Vision By Deep Learning (CS4245) 2021 from the Delft University of Technology. Creating the dataset has been carried out in collaboration with the company Hoogenboom Alstroemeria.