Individual fairness is an intuitive definition of algorithmic fairness that addresses some of the drawbacks of group fairness. Despite its benefits, it depends on a task specific fair metric that encodes our intuition of what is fair and unfair for the ML task at hand, and the lack of a widely accepted fair metric for many ML tasks is the main barrier to broader adoption of individual fairness. In this paper, we present two simple ways to learn fair metrics from a variety of data types. We show empirically that fair training with the learned metrics leads to improved fairness on three machine learning tasks susceptible to gender and racial biases. We also provide theoretical guarantees on the statistical performance of both approaches.

Neural networks have been shown to perform incredibly well in classification tasks over structured high-dimensional datasets. However, the learning dynamics of such networks is still poorly understood. In this paper we study in detail the training dynamics of a simple type of neural network: a single hidden layer trained to perform a classification task. We show that in a suitable mean-field limit this case maps to a single-node learning problem with a time-dependent dataset determined self-consistently from the average nodes population. We specialize our theory to the prototypical case of a linearly separable dataset and a linear hinge loss, for which the dynamics can be explicitly solved. This allow us to address in a simple setting several phenomena appearing in modern networks such as slowing down of training dynamics, crossover between rich and lazy learning, and overfitting.

Precise and reliable estimation of reference evapotranspiration (ET o ) is an essential for the irrigation and water resources management. ET o is difficult to predict due to its complex processes. This complexity can be solved using machine learning methods. This study investigates the performance of artificial neural network (ANN) and deep neural network (DNN) models for estimating daily ET o . Previously proposed ANN and DNN methods have been realized, and their performances have been compared. Six input data including maximum air temperature (T max ), minimum air temperature (T min ), solar radiation (R n ), maximum relative humidity (RH max ), minimum relative humidity (RH min ) and wind speed (U 2 ) are used from 4 meteorological stations (Adana, Aksaray, Isparta and Ni\u{g}de) during 1999-2018 in Turkey. The results have shown that our proposed DNN models achieves satisfactory accuracy for daily ET o estimation compared to previous ANN and DNN models. The best performance has been observed with the proposed model of DNN with SeLU activation function (P-DNN-SeLU) in Aksaray with coefficient of determination (R 2 ) of 0.9934, root mean square error (RMSE) of 0.2073 and mean absolute error (MAE) of 0.1590, respectively. Therefore, the P-DNN-SeLU model could be recommended for estimation of ET o in other climate zones of the world.

The most advanced framework for dense pose estimation for chimpanzees. It will help primatologists and other scientists study how chimps across Africa behave in the wild and in captive settings. The framework leverages a large-scale data set of unlabeled videos in the wild, a pretrained dense pose estimator for humans, and dense self-training techniques. This is a joint project in collaboration with our partners the Max Planck Institute for Evolutionary Anthropology (MPI EVA) and the Pan African Programme: The Cultured Chimpanzee, and their network of collaborators. We show that we can train a model to detect and recognize chimpanzees by transferring knowledge from existing detection, segmentation, and human dense pose labeling models.

Covid-19 patients in the UK are being treated with dexamethasone today after a UK trial of the drug found it could save lives. "The treatment is immediately available and already in use on the NHS," said health minister Matt Hancock. "It is not by any means a cure but it is the best news we have had," Hancock told parliament today. The UK's chief medical officers say it should be used immediately, according to the BBC. A preliminary study found that the steroid, which is already widely prescribed for treating allergies and asthma, reduces the risk of dying from covid-19 by a third for patients on ventilators, and by a fifth for those receiving oxygen. Dexamethasone should only be taken if prescribed by a doctor. Officials in Beijing, China confirmed 31 new coronavirus cases today, bringing the total to 137 in the last six days. The city is again restricting all non-essential travel. Schools, swimming pools and gyms are all closed from today.

In this session, we will be going through some of the fundamental methods that are used to tackle Natural Language Processing (NLP) problems. We will first be going through some NLP theory and then will walk through some code showing how a sentiment analysis model can be trained from scratch on a real-world IMDB movie review dataset.

Mobilized Construction are global providers of data and AI analytics. This data identifies road network quality and highlights areas in need of improvement. To collect this data they use a custom sensor that can attach to any moving vehicle, on any road, globally. Their solutions have been used in every type of road environment, seeing them work around the world, including the United Kingdom, Kenya, and Uganda. With a strong focus on optimising the speed at which a pothole is recognised from when it first develops, Mobilized had the hardware to collect data on potholes but no way of utilising this valuable information.

When Lauren Dry heard last year that facial recognition cameras were being trialled in the suburb of East Perth, she thought it was a joke. "I just thought to myself: What do you mean facial recognition cameras, that's sci-fi! That doesn't happen in Perth," she told 7.30. "And I looked into it and I was, like, this is real." Ms Dry enjoys a quiet life at home with her young family in Perth's leafy suburbs.

At The Good AI, we strongly believe Artificial Intelligence (AI) should be inclusive and celebrate diversity. However, AI is also the reflector of its creators and this translates into the reproduction of certain biases into AI products related to race, gender or sexual orientation among others. The following article from the MIT Technology Review explains how. In the light of this, the tech industry has an important responsibility towards society, and the death of George Floyd at the hands of a city police officer in Minneapolis, USA on 25 May 2020, -one in a long series of racists attacks against African Americans -, should urge us to take action. We need to make sure we are not perpetuating and letting racism or any other kind of discrimination take roots in our AI systems.

Our company has built a platform to produce high-quality cells and tissues for regenerative medicine. That pursuit involves multiple disciplines, which means everyone here is an expert in a different language. Some of us are fluent in stem-cell biology, others in optical engineering, others in machine learning. When we started the company it wasn't possible to do biology and engineering under the same roof. When we finally moved into a shared space we were able to learn each other's lexicons, and we became more strongly aligned.