DYDAS EU announces the winner of the Call for ideas Contest The Call for Ideas Contest is a Contest lauched by DYDAS EU funded by the European Commission (CEF Telecom Open Data program) and it consisted in presenting an idea of a new and innovative service for cities or citizens that could be provided through […]
Imagine you work as an AI developer and your team has trained an image classification model. The validation and testing step was successful and your model shows a pretty good accuracy, precision and recall; let’s say about 0.98, 0.97 and 0.99, respectively. Great. However, the model has to make important decisions based on its own […]
In a machine learning project, much emphasis is often placed on the model development phase, where data scientists can walk through all the steps necessary to build a successful and robust prototype. These steps are widely consolidated and consist of data collection, proper labeling, model selection, training, performance evaluation on the test set, and final […]
A brief history Since the early 2000s, Deep Learning began to take shape through the development of the first libraries, such as Matlab, Torch and OpenNN, which helped statisticians and mathematicians with the implementation of the first DL models. Through the years, the advance of technology and the introduction of more computing power with the […]
What are the trends in deep learning for 2023? The simplest answer to this question is: countless. Growing research in deep learning, advancing technologies and increasing computational power make it possible to prototype and put into production systems that even a few years ago were prohibitively expensive. Here are some of the most interesting applications […]
When training a Machine Learning or Deep Learning model, a crucial phase is evaluation. It consists of measuring how well the model is capable of yielding the expected results in terms of prediction. The dataset is usually divided into three sets: train, validation and test. The first one is used for training, the second one […]
Deep Learning models require large amount of data to be trained. Any use case requiring the processing of data like: images, videos, full names, addresses, sensitive information and so on. This represents a potential risk for privacy breaches. For this reason, there are different methods for protecting data during training and others during the inference […]
AN IDEA TO IMPROVE SERVICES AND CITIZENS’ LIVES The contest consists in presenting an idea of a new and innovative service for cities or citizens that can be provided through the DYDAS platform as a key component. The participants must describe the service and all its components and how this service can help cities and/or […]
Nel mese di settembre si terrà il 2×1 HACKATHON – Shed Light-on red traffic lights and urban greenery status, organizzato da Fiware. L’hackathon virtuale sarà un concorso di idee innovative per lo sviluppo di nuovi servizi, soluzioni o applicazioni intelligenti nel settore della Smart Mobility, della gestione delle aree verdi urbane e degli open data. […]
