deeplearning4j

Objects detection with YOLO technique using Deeplearning4j

Detecting objects in an image can be accomplished in a variety of ways, but among them YOLO (You Only Look Once) is by far the most easy and efficient one. Since YOLO is based on deep learning and deep learning has two faces (training and testing/execution) you may be wondering which side of the coin we will focus on here. Well, the process of training a neural network may be a complex task that requires time, powerful hardware (possibly GPU+Cuda), expertise in the specific field and a trial and error scientific approach. Here instead we will see how to use [...]

Di |2020-07-01T17:07:52+00:00giugno 30th, 2020|

Convolutional Neural Networks with Eclipse Deeplearning4j

In the previous article we have seen how to use Eclipse Deeplearning4j for building, training and testing a simple and classic MLP  (Multi Layer Perceptron) neural network. As a dataset we used the "hello world" example of deep learning, that is the MNIST: a dataset of 70,000 b/w images of 28×28 pixels, representing handwritten 0-9 digits. Now we will explore a different architecture known as Convolutional Neural Network (CNN), which is very powerful, particularly when dealing with image classification tasks. After having explained how this network works and why it is so efficient, then we will take our previous MLP example, [...]

Di |2020-07-02T07:46:47+00:00febbraio 2nd, 2020|

EclipseCon 2019: deep learning & other cool stuff

Since 2008 I missed only one EclipseCon Europe, the annual Eclipse Conference held in Ludwigsburg, Germany. This year the program committee accepted a talk from us about deep learning in general and DL4J as an Eclipse Project. Having a talk accepted from the committee is always an honour and a pleasure, but this time it was particularly special for a couple of reasons: it was the only talk about deep learnig in the program and ... well, it was scheduled in the forum theatre, where keynotes, announcements, welcome and important talks and closing sessions are held. Therefore, when I entered [...]

Di |2020-03-31T04:00:44+00:00novembre 9th, 2019|

Build your first neural network with Eclipse Deeplearning4j

In the previous article we had an introduction to deep learning and neural networks. Here we will explore how to design a network depending on the task we want to solve. There is indeed an incredibly high number of parameters and topology choices to deal with when working with neural networks: how many hidden layers should I set up? What activation function should they use? What are good values for the learning rate? Should I use a classical Multilayer Neural Network, a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN) or one of the other architectures available? These questions are [...]

Di |2020-03-28T17:31:41+00:00giugno 2nd, 2019|

Introduzione al Deep Learning

Leggete e sentite parlare continuamente di Deep Learning e vorreste conoscere alcune basi di questo argomento? Bene, allora continuate a leggere: in questo articolo vi farò una semplice introduzione alle fondamenta del deep learning, valida a prescindere dal linguaggio, libreria o framework che potreste scegliere in futuro.   Che cos'è il deep learning? Va chiarito subito che tentare di spiegare il deep learning in modo adeguato richiederebbe un bel po' di tempo e non è lo scopo di questo articolo. L'obiettivo qui è quello di aiutare il principiante a capire le basi dell'argomento. Tuttavia anche un esperto potrebbe trovare qualche [...]

Di |2020-03-28T17:49:11+00:00agosto 10th, 2018|
Torna in cima