Artificial neural network
Artificial neural networks ( ANN ) or connectionist systems are computing systems vaguely inspired by the biological neural networks that constitute animal brains . [1] The neural network itself is not an algorithm, but rather a framework for many different machine learning algorithms to work together and process complex data inputs. [2] Such systems "learn" to perform tasks by considering examples, generally without being programmed with any task-specific rules. For example, in image recognition , they might learn to identify images that contain cats by analyzing example images that have been manually labeled as "cat" or "no cat" and using the results to identify cats in other images. They do this without any prior knowledge about cats, for example, that they have fur, tails, whiskers and cat-like faces. Instead, they automatically generate identifying characteristics from the learning material that they process.
Page Revisions
| Year | Metadata | Sections | Top Words | First Paragraph |
| 2018 |
769829 characters 74 sections 185 paragraphs 15 images 690 internal links 404 external links |
displaystyle 0.571 textstyle 0.366 neural 0.361 learning 0.213 boldsymbol 0.156 weights 0.123 neurons 0.120 w_ 0.120 backpropagation 0.108 networks 0.103 neuron 0.099 x_ 0.096 artificial 0.092 lstm 0.090 training 0.090 |
Artificial neural networks ( ANN ) or connectionist systems are computing systems vaguely inspired by the biological neural networks that constitute animal brains . [1] The neural network itself is not an algorithm, but rather a framework for many different machine learning algorithms to work together and process complex data inputs. [2] Such systems "learn" to perform tasks by considering examples, generally without being programmed with any task-specific rules. For example, in image recognition , they might learn to identify images that contain cats by analyzing example images that have been manually labeled as "cat" or "no cat" and using the results to identify cats in other images. They do this without any prior knowledge about cats, for example, that they have fur, tails, whiskers and cat-like faces. Instead, they automatically generate identifying characteristics from the learning material that they process. |
|
| 2017 |
637274 characters 65 sections 168 paragraphs 15 images 446 internal links 346 external links |
displaystyle 0.520 textstyle 0.398 neural 0.378 learning 0.222 boldsymbol 0.181 neurons 0.150 backpropagation 0.109 weights 0.108 networks 0.106 lstm 0.105 deep 0.102 layers 0.087 training 0.087 neuron 0.080 hidden 0.080 |
Artificial neural networks ( ANNs ) or connectionist systems are computing systems inspired by the biological neural networks that constitute animal brains. Such systems learn (progressively improve performance on) tasks by considering examples, generally without task-specific programming. For example, in image recognition , they might learn to identify images that contain cats by analyzing example images that have been manually labeled as "cat" or "no cat" and using the results to identify cats in other images. They do this without any a priori knowledge about cats, e.g., that they have fur, tails, whiskers and cat-like faces. Instead, they evolve their own set of relevant characteristics from the learning material that they process. |
|
| 2016 |
273316 characters 38 sections 96 paragraphs 13 images 350 internal links 94 external links |
3. Employing artificial neural networks |
neural 0.570 textstyle 0.540 displaystyle 0.389 learning 0.170 neurons 0.163 networks 0.117 artificial 0.098 training 0.094 network 0.058 recognition 0.058 g_ 0.057 turing 0.054 biological 0.052 weights 0.049 x_ 0.047 |
Neural networks (also referred to as connectionist systems ) are a computational approach which is based on a large collection of neural units loosely modeling the way a biological brain solves problems with large clusters of biological neurons connected by axons. Each neural unit is connected with many others, and links can be enforcing or inhibitory in their effect on the activation state of connected neural units. Each individual neural unit may have a summation function which combines the values of all its inputs together. There may be a threshold function or limiting function on each connection and on the unit itself such that it must surpass it before it can propagate to other neurons. These systems are self-learning and trained rather than explicitly programmed and excel in areas where the solution or feature detection is difficult to express in a traditional computer program. |
| 2015 |
247133 characters 35 sections 91 paragraphs 13 images 324 internal links 70 external links |
4. Employing artificial neural networks |
textstyle 0.597 neural 0.497 displaystyle 0.402 learning 0.175 neurons 0.161 artificial 0.112 networks 0.098 training 0.088 network 0.062 g_ 0.059 biological 0.058 weights 0.057 backpropagation 0.056 recognition 0.056 models 0.049 |
In machine learning and cognitive science , artificial neural networks ( ANNs ) are a family of models inspired by biological neural networks (the central nervous systems of animals, in particular the brain ) and are used to estimate or approximate functions that can depend on a large number of inputs and are generally unknown. Artificial neural networks are generally presented as systems of interconnected " neurons " which exchange messages between each other. The connections have numeric weights that can be tuned based on experience, making neural nets adaptive to inputs and capable of learning. |
| 2014 |
229922 characters 35 sections 84 paragraphs 10 images 308 internal links 57 external links |
4. Employing artificial neural networks |
scriptstyle 0.615 neural 0.483 displaystyle 0.395 learning 0.178 neurons 0.156 artificial 0.107 networks 0.096 recognition 0.078 training 0.074 g_ 0.060 network 0.059 biological 0.059 weights 0.051 dewdney 0.050 x_ 0.050 |
In machine learning , artificial neural networks ( ANNs ) are a family of statistical learning algorithms inspired by biological neural networks (the central nervous systems of animals, in particular the brain ) and are used to estimate or approximate functions that can depend on a large number of inputs and are generally unknown. Artificial neural networks are generally presented as systems of interconnected " neurons " which can compute values from inputs, and are capable of machine learning as well as pattern recognition thanks to their adaptive nature. |
| 2013 |
224212 characters 32 sections 85 paragraphs 11 images 271 internal links 51 external links |
4. Employing artificial neural networks 7. Types of artificial neural networks |
scriptstyle 0.616 neural 0.479 displaystyle 0.395 learning 0.171 neurons 0.156 artificial 0.107 networks 0.094 recognition 0.078 training 0.074 network 0.063 dewdney 0.060 g_ 0.060 biological 0.059 weights 0.057 models 0.052 |
In computer science and related fields, artificial neural networks are computational models inspired by animals' central nervous systems (in particular the brain ) that are capable of machine learning and pattern recognition . They are usually presented as systems of interconnected " neurons " that can compute values from inputs by feeding information through the network. |
| 2012 |
178139 characters 31 sections 68 paragraphs 11 images 179 internal links 37 external links |
3. Employing artificial neural networks 6. Types of artificial neural networks |
scriptstyle 0.683 displaystyle 0.439 neural 0.383 neurons 0.148 learning 0.136 artificial 0.105 networks 0.076 dewdney 0.065 g_ 0.065 network 0.056 weights 0.056 x_ 0.054 biological 0.054 s_ 0.053 training 0.049 |
An artificial neural network , often just called a neural network , is a mathematical model inspired by biological neural networks . A neural network consists of an interconnected group of artificial neurons , and it processes information using a connectionist approach to computation . In most cases a neural network is an adaptive system that changes its structure during a learning phase. Neural networks are used to model complex relationships between inputs and outputs or to find patterns in data. |
| 2011 |
160690 characters 31 sections 67 paragraphs 9 images 186 internal links 32 external links |
3. Employing artificial neural networks |
scriptstyle 0.693 displaystyle 0.445 neural 0.366 neurons 0.157 learning 0.126 artificial 0.110 dewdney 0.066 g_ 0.066 training 0.066 weights 0.064 network 0.063 networks 0.061 biological 0.060 ann 0.055 synapses 0.055 |
An artificial neural network (ANN) , usually called neural network (NN) , is a mathematical model or computational model that is inspired by the structure and/or functional aspects of biological neural networks . A neural network consists of an interconnected group of artificial neurons , and it processes information using a connectionist approach to computation . In most cases an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network during the learning phase. Modern neural networks are non-linear statistical data modeling tools. They are usually used to model complex relationships between inputs and outputs or to find patterns in data. |
| 2010 |
155665 characters 31 sections 67 paragraphs 9 images 180 internal links 28 external links |
3. Employing artificial neural networks |
scriptstyle 0.681 displaystyle 0.437 neural 0.378 neurons 0.160 learning 0.132 artificial 0.112 weights 0.072 network 0.070 dewdney 0.067 g_ 0.067 synapses 0.067 training 0.067 networks 0.062 biological 0.061 x_ 0.056 |
An artificial neural network (ANN) , usually called neural network (NN) , is a mathematical model or computational model that is inspired by the structure and/or functional aspects of biological neural networks . A neural network consists of an interconnected group of artificial neurons , and it processes information using a connectionist approach to computation . In most cases an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network during the learning phase. Modern neural networks are non-linear statistical data modeling tools. They are usually used to model complex relationships between inputs and outputs or to find patterns in data. |
| 2009 |
160201 characters 50 sections 81 paragraphs 11 images 206 internal links 29 external links |
displaystyle 0.534 neural 0.489 learning 0.217 neurons 0.162 network 0.159 networks 0.133 recurrent 0.119 training 0.113 artificial 0.108 weights 0.107 hidden 0.098 ann 0.091 g_ 0.091 regression 0.076 hopfield 0.076 |
An artificial neural network (ANN) , usually called "neural network" (NN), is a mathematical model or computational model that tries to simulate the structure and/or functional aspects of biological neural networks . It consists of an interconnected group of artificial neurons and processes information using a connectionist approach to computation . In most cases an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network during the learning phase. Neural networks are non-linear statistical data modeling tools. They can be used to model complex relationships between inputs and outputs or to find patterns in data. |
|
| 2008 |
148858 characters 49 sections 82 paragraphs 8 images 181 internal links 23 external links |
displaystyle 0.542 neural 0.473 learning 0.220 neurons 0.165 network 0.156 networks 0.135 recurrent 0.121 training 0.114 weights 0.108 artificial 0.104 hidden 0.099 ann 0.092 g_ 0.092 regression 0.077 hopfield 0.077 |
An artificial neural network (ANN) , often just called a "neural network" (NN), is a mathematical model or computational model based on biological neural networks . It consists of an interconnected group of artificial neurons and processes information using a connectionist approach to computation . In most cases an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network during the learning phase. |
|
| 2007 |
140488 characters 44 sections 79 paragraphs 8 images 162 internal links 14 external links |
displaystyle 0.577 neural 0.470 learning 0.229 network 0.151 neurons 0.142 networks 0.128 recurrent 0.109 training 0.106 artificial 0.104 hidden 0.099 ann 0.091 g_ 0.091 weights 0.078 regression 0.076 hopfield 0.076 |
An artificial neural network (ANN), often just called a "neural network" (NN), is a mathematical model or computational model based on biological neural networks . It consists of an interconnected group of artificial neurons and processes information using a connectionist approach to computation . In most cases an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network during the learning phase. |
|
| 2006 |
163125 characters 45 sections 95 paragraphs 7 images 176 internal links 24 external links |
displaystyle 0.555 neural 0.417 learning 0.219 neurons 0.152 x_ 0.146 network 0.145 networks 0.140 training 0.132 sum 0.124 weights 0.120 perceptrons 0.109 _ 0.105 perceptron 0.098 function 0.088 layer 0.088 |
An artificial neural network (ANN) or commonly just neural network (NN) is an interconnected group of artificial neurons that uses a mathematical model or computational model for information processing based on a connectionist approach to computation . In most cases an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network. |
|
| 2005 |
130270 characters 42 sections 81 paragraphs 5 images 132 internal links 22 external links |
displaystyle 0.542 neural 0.477 learning 0.210 neurons 0.195 networks 0.174 training 0.135 network 0.132 hidden 0.114 neuron 0.106 perceptron 0.106 perceptrons 0.106 weights 0.101 ann 0.100 function 0.093 recurrent 0.092 |
An artificial neural network (ANN), also called a simulated neural network (SNN) (but the term neural network (NN) is grounded in biology and refers to very real, highly complex plexus), is an interconnected group of artificial neurons that uses a mathematical or computational model for information processing based on a connectionist approach to computation . There is no precise agreed definition among researchers as to what a neural network is, but most would agree that it involves a network of highly complex processing elements ( neurons ), where the global behaviour is determined by the connections between the processing elements and element parameters. Since anything approaching a full appreciation of neuronal function remains a distant dream, and since the factors producing global output result from many non-linear, modulating, and poorly understood real-time feedback signals within a single neuron, the highly linear artificial networks (where 'neurons' are modeled as input/output nodes) are perceived as academic research tools rather than even a distant representation of brain function. The original inspiration for the technique was from examination of the central nervous system and the neurons (and their axons , dendrtites and synapses ) which constitute one of its most significant information processing elements (see Neuroscience ). In a neural network model, simple nodes (called variously "neurons", "neurodes", "PEs" ("processing elements") or "units") are connected together to form a network of nodes — hence the term "neural network". The term also includes implementations purely in software that may run on general purpose computers. |
|
| 2004 |
35322 characters 17 sections 36 paragraphs 1 images 58 internal links 9 external links |
neural 0.521 neurons 0.300 weights 0.235 network 0.198 training 0.195 perceptron 0.193 neuron 0.150 networks 0.150 recurrent 0.150 learning 0.131 perceptrons 0.129 activation 0.118 nodes 0.113 backpropagation 0.107 descent 0.107 |
A neural network is an interconnected group of neurons. The prime examples are of course biological neural networks , especially the human brain . In modern usage, researchers often refer to an artificial neural network (ANN) simply as a neural network or neural net for short, and this is the sense that is used in the rest of this article. |
|
| 2003 |
24959 characters 19 sections 30 paragraphs 0 images 46 internal links 5 external links |
neural 0.537 weights 0.257 training 0.230 perceptron 0.202 neurons 0.199 network 0.181 learning 0.166 networks 0.132 backpropagation 0.127 descent 0.127 perceptrons 0.127 sigmoid 0.123 nodes 0.120 optimization 0.119 layer 0.112 |
An artificial neural network , more commonly known as a neural network or neural net for short, is a mathematical model for information processing based on a connectionist approach to computation. The original inspiration for the technique was from examination of bioelectrical networks in the brain formed by neurons and their synapses . In a neural network model, simple nodes (or "neurons", or "units") are connected together to form a network of nodes - hence the term "neural network". |
|
| 2002 |
10715 characters 11 sections 20 paragraphs 0 images 5 internal links 0 external links |
neural 0.552 nodes 0.349 weights 0.291 neurons 0.217 perceptron 0.207 node 0.163 network 0.138 optimization 0.130 neuron 0.124 calculation 0.124 networks 0.117 output 0.108 brain 0.102 fires 0.101 massively 0.101 |
Neural networks , or more properly Artificial neural networks are computer systems based on a connectionist approach to computation. Simple nodes (or "neurons", or "units") are connected together to form a network of nodes - hence the term "neural network". The original inspiration for the technique was from examination of the structures of the brain , and particularly an examination of neurons . |
|
| 2001 |
6865 characters 2 sections 19 paragraphs 0 images 4 internal links 0 external links |
neural 0.508 nodes 0.393 weights 0.255 neurons 0.244 perceptron 0.233 node 0.183 calculation 0.140 network 0.133 learning 0.122 networks 0.122 organizing 0.122 brain 0.115 fires 0.114 massively 0.114 correct 0.113 |
Neural networks , or more properly Artificial neural networks are computer systems based on a connectionist approach to computation. Simple nodes (or "neurons", or "units") are connected together to form a network of nodes - hence the term "neural network". The orginal inspiration for the technique was from examination of the structures of the brain , and particularly an examination of neurons . |