Goto

Collaborating Authors

Neural Networks


Pytorch is growing, Tensorflow is not.

#artificialintelligence

One way to measure the adoption of a framework is to count how many papers wrote their codes on each framework. The website PapersWhitCode counts only the papers that have code implementation on repositories. So, to clarify, we can say that this trend is to open researches. The graph shows the trends in the last 5 years by the percentage of frameworks used. From the last year, Pytorch is clearly growing, but Tensorflow is not.


Deep Learning Neural Networks Bas

#artificialintelligence

Image recognition, when referring to a computer, is its ability to understand the content of the photograph when it sees it. For instance, when a "House" picture is passed through a neural network, and it outputs the label'House,' this is because it recognized the house as the main content of the picture. In previous years, researchers have used neural networks to make significant progress in image recognition. Neural networks can be employed in object effectively, and its recognition accuracy will be high. Neurons are separate nodes that make up a neural network and are arranged in various groups known as layers.


Diagnosing Pneumonia from Chest X-Rays by Image-Based Deep Learning using Neural Networks

#artificialintelligence

This article is to set up the framework with a simple model with a detailed walk through of each step. There are tons of improvements that can be made to boost model performance! In the world of healthcare, one of the major issues that medical professionals face is the correct diagnosis of conditions and diseases of patients. Not being able to correctly diagnose a condition is a problem for both the patient and the doctor. The doctor is not benefiting the patient in the appropriate way if the doctor misdiagnoses the patient.


Setting up your Nvidia GPU for Deep Learning(2020)

#artificialintelligence

This article aims to help anyone who wants to set up their windows machine for deep learning. Although setting up your GPU for deep learning is slightly complex the performance gain is well worth it * . The steps I have taken taken to get my RTX 2060 ready for deep learning is explained in detail. The first step when you search for the files to download is to look at what version of Cuda that Tensorflow supports which can be checked here, at the time of writing this article it supports Cuda 10.1.To download cuDNN you will have to register as an Nvidia developer. I have provided the download links to all the software to be installed below.


LiteDepthwiseNet: A Lightweight Neural Network for Hyperspectral Image Classification

#artificialintelligence

Hyperspectral images (HSIs) are a kind of optical remote sensing image with a high spectral resolution. Hyperspectral images (HSIs) have attracted much attention recently as they possess unique properties and contain massive information. The newly developed deep learning methods are applied successfully in HSI classification, achieving higher accuracy than traditional methods. The earlier DL-based HSI classification methods were based on fully connected neural networks, such as stacked autoencoders (SAEs) and recursive autoencoders (RAEs). Therefore, they destroyed the spatial structure information of an HSI as they could only handle one-dimensional vectors.


Deep-Learning AI Just Found Nearly 2 Billion Trees in the Sahara Desert

#artificialintelligence

There are many more trees in the West African Sahara Desert than we thought, according to a recent study based on AI and satellite imagery and published in the journal Nature -- which found more than 1.8 billion trees in the Sahara Desert. Researchers have counted more than 1.8 billion trees and shrubs in the 501,933 square-mile (1.3 million square-kilometer) area -- in an area encompassing the western-most region of the Sahara Desert -- called the Sahel -- along with sub-humid zones of West Africa, reports The World Economic Forum. "We were very surprised to see that quite a few trees actually grow in the Sahara Desert, because up until now, most people thought that virtually none existed," said Professor Martin Brandt from the geosciences and natural resource management department of the University of Copenhagen and lead author of the recent study. "We counted hundreds of millions of trees in the desert alone. Doing so wouldn't have been possible without this technology," explained Brandt, according to a blog post on the University of Copenhagen's website.


Top 10 Deep Learning Frameworks for Every Data Scientist

#artificialintelligence

Deep learning framework with an interface or a library/tool helps Data Scientists and ML Developers to bring the deep learning models into life. Deep Learning a sub-branch of machine learning, that puts efficiency and accuracy on the table, when it is trained with a vast amounts of bigdata. TensorFlow developed by the Google Brain team, is inarguably one of the most popular deep learning frameworks. It supports Python, C, and R to create deep learning models along with wrapper libraries. It is available on both desktop and mobile.


Q: How does hydrogen turn into a metal? A: Hang on a second, I need to train my AI supercomputer first

#artificialintelligence

Scientists have trained a neural network on a supercomputer to simulate how hydrogen turns into a metal, an experiment impossible to reproduce physically on Earth. Under extreme pressures and high enough temperatures – such as in the cores of Jupiter, Saturn, Uranus, and Neptune – hydrogen enters a strange phase. The electrons normally bound to its nuclei are free to move, and they collectively whiz around to conduct electricity, a common property in metals. The physics behind the process is difficult to study. Attempting to replicate the conditions inside those planet cores here on Earth is pointless – the sheer amount of energy required is impractical.


Microsoft releases preview of Lobe training app for machine-learning

ZDNet

Microsoft is continuing to look for ways to make machine-learning technology easier to use. In 2018, Microsoft bought Lobe, a San Francisco-based startup that made a platform for building, training and shipping custom deep-learning models. This week, Microsoft made some of Lobe's technology publicly available. Available for both Windows and Mac, the Lobe app is free and designed to enable people with no data science experience to import images into the app and label them to create a machine learning dataset. According to Microsoft, "Lobe automatically selects the right machine learning architecture and starts training without any setup or configuration."


AstraZeneca is using PyTorch-powered algorithms to discover new drugs

#artificialintelligence

Since it launched in 2017, Facebook's machine-learning framework PyTorch has been put to good use, with applications ranging from powering Elon Musk's autonomous cars to driving robot-farming projects. Now pharmaceutical firm AstraZeneca has revealed how its in-house team of engineers are tapping PyTorch too, and for equally as important endeavors: to simplify and speed up drug discovery. Combining PyTorch with Microsoft Azure Machine Learning, AstraZeneca's technology can comb through massive amounts of data to gain new insights about the complex links between drugs, diseases, genes, proteins or molecules. Those insights are used to feed an algorithm that can, in turn, recommend a number of drug targets for a given disease for scientists to test in the lab. The method could allow for huge strides in a sector like drug discovery, which so far has been based on costly and time-consuming trial-and-error methods.