Deep learning


Topic | v1 | created by janarez |
Description

Deep learning (also known as deep structured learning) is part of a broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised. Deep learning architectures such as deep neural networks, deep belief networks, recurrent neural networks and convolutional neural networks have been applied to fields including computer vision, machine vision, speech recognition, natural language processing, audio recognition, social network filtering, machine translation, bioinformatics, drug design, medical image analysis, material inspection and board game programs, where they have produced results comparable to and in some cases surpassing human expert performance. Artificial neural networks (ANNs) were inspired by information processing and distributed communication nodes in biological systems.


Relations

a parent of Computer vision

Computer vision is an interdisciplinary scientific field that deals with how computers can gain high-...

a subtopic of Computer science

Computer science is the study of computation and information. Computer science deals with theory of c...

relates to Machine learning

Machine learning (ML) is the study of computer algorithms that improve automatically through experien...

uses Computer programming

Computer programming is the process of designing and building an executable computer program to accom...

a subtopic of Artificial intelligence (AI)

Artificial intelligence (AI), is intelligence demonstrated by machines, unlike the natural intelligen...

a tool for Data science

Data science is an inter-disciplinary field that uses scientific methods, processes, algorithms and s...

relates to Big data

Big data is a field that treats ways to analyze, systematically extract information from, or otherwis...

a parent of Graph convolutional networks (GCN)

Generalization of neural networks to arbitrary graphs.

uses Backpropagation

In machine learning, backpropagation (backprop, BP) is a widely used algorithm for training feedforwa...


Edit topic New topic

Resources

No beginner resources matching your criteria have been registered, yet.

is treated in Deep Reinforcement Learning | ÚFAL

10.0 rating 5.0 level 10.0 clarity 4.0 background – 1 rating

In recent years, reinforcement learning has been combined with deep neural networks, giving rise to g...

is treated in Deep Learning

9.5 rating 5.0 level 8.5 clarity 5.0 background – 2 ratings

In recent years, deep neural networks have been used to solve complex machine-learning problems. They...

is treated in Deep Learning

9.0 rating 5.0 level 7.0 clarity 5.0 background – 1 rating

The Deep Learning textbook is a resource intended to help students and practitioners enter the field...

is applicable to Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition

6.5 rating 6.0 level 7.0 clarity 4.5 background – 2 ratings

Human activity recognition (HAR) tasks have traditionally been solved using engineered features obta...

is applicable to DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices

6.0 rating 8.0 level 6.0 clarity 2.5 background – 2 ratings

In this work, we present the design and implementation of DeepX, a software accelerator for deep lear...

is treated in Dive into Deep Learning

Interactive deep learning book with code, math, and discussions Implemented with NumPy/MXNet, PyTo...

is treated in LabML Neural Networks

This is a collection of simple PyTorch implementations of neural networks and related algorithms. The...

is applicable to Deep Learning in Computer Vision

Deep learning added a huge boost to the already rapidly developing field of computer vision. With dee...

is applicable to Sentiment Analysis with Deep Learning using BERT

In this 2-hour long project, you will learn how to analyze a dataset for sentiment analysis. You will...

is applicable to Deep Residual Learning for Image Recognition

Deeper neural networks are more difficult to train. We present a residual learning framework to ease...

is applicable to Going deeper with convolutions

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new...