Neural network

Summary

A neural network can refer to a neural circuit of biological neurons (sometimes also called a biological neural network), a network of artificial neurons or nodes in the case of an artificial neural network. Artificial neural networks are used for solving artificial intelligence (AI) problems; they model connections of biological neurons as weights between nodes. A positive weight reflects an excitatory connection, while negative values mean inhibitory connections. All inputs are modified by a weight and summed. This activity is referred to as a linear combination. Finally, an activation function controls the amplitude of the output. For example, an acceptable range of output is usually between 0 and 1, or it could be −1 and 1. These artificial networks may be used for predictive modeling, adaptive control and applications where they can be trained via a dataset. Self-learning resulting from experience can occur within networks, which can derive conclusions from a complex and seem

Official source

https://en.wikipedia.org/wiki/Neural_network

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related publications (100)

Related publications

Related people (160)

Related people

Related units (73)

Related units

Related concepts (93)

Related concepts

Related courses (90)

Machine learning and data analysis are becoming increasingly central in sciences including physics. In this course, fundamental principles and methods of machine learning will be introduced and practised.

This course aims to introduce the basic principles of machine learning in the context of the digital humanities. We will cover both supervised and unsupervised learning techniques, and study and implement methods to analyze diverse data types, such as images, music and social network data.

Since 2010 approaches in deep learning have revolutionized fields as diverse as computer vision, machine learning, or artificial intelligence. This course gives a systematic introduction into influential models of deep artificial neural networks, with a focus on Reinforcement Learning.

Related courses

Related lectures (246)

Related lectures

Learning-based approaches for feature fusion in multi-modal indoor localization

Vincent Cabrini

Due to their aptitude to capture complex dependencies, neural networks are a promising candidate for indoor localization. Omnipresent phenomena such as multi-path signal propagation, shadowing and device noise introduce non-linear effects in the data, and make conventional geometry-based methods fail even in simple environments. This semester project explores few analytical outlier rejection algorithms and new fusion methods based on neural networks and compares them with an analytical model.

2020

The goal of this project was to work on room occupancy and to provide solutions and ideas on how to detect if a room is occupied or not using generic and non expensive sensors. This is motivated by the fact that buildings account for 50% of the total energy consumption in the US and 30% of it is wasted mainly due to a bad management of light, heating, cooling and ventilation systems. Being able to know if rooms are occupied or not would then enable us to automatize these systems and make them more energy efficient. The sensors studied in the process were a CO2, relative humidity and temperature sensor, a camera, a WiFi sniffer and a PIR(Passive infrared) sensor. All of them were implemented and tested to see how they could measure occupancy. After analyzing each sensor alone we had to combine them to obtain the best possible accuracy. To do so, two methods were tried. The first using all the sensors mentioned was tested and the accuracy achieved was 93%. The second was based on the use of neural network on images provided by the camera to detect people and the accuracy was 97%.

2021

DeepSuccess - Predict the Success of Tech Startups

Davide Di Dio

Many interesting applications emerged with the increasing popularity of deep learning. This project explored natural language processing and visualization techniques as well as two neural network architectures to classify ICOs. The first network focused on the ICOs white-paper with a bi-directional LSTM attention network. The second targeted the ICOs website structure with a Graph neural network as well as page topics with Latent Dirichlet Analysis.

2019