Artificial neural network - Wikipedia, the free encyclopedia

This link has been bookmarked by 100 people . It was first bookmarked on 03 Aug 2006, by Antonia Haller.

15 Dec 14

kronayne91
MOSFET_operation
- artificial neural networks (ANNs) are a family of statistical learning algorithms
- used to estimate or approximate functions that can depend on a large number of inputs and are generally unknown.
- In an Artificial Neural Network, simple artificial nodes, known as "neurons", "neurodes", "processing elements" or "units", are connected together to form a network which mimics a biological neural network.
- consist of sets of adaptive weights, i.e. numerical parameters that are tuned by a learning algorithm
- capable of approximating non-linear functions of their inputs
- The adaptive weights are conceptually connection strengths between neurons, which are activated during training and prediction.
- Neural network models which emulate the central nervous system are part of theoretical neuroscience and computational neuroscience.
- The first issue was that single-layer neural networks were incapable of processing the exclusive-or circuit. The second significant issue was that computers were not sophisticated enough to effectively handle the long run time required by large neural networks. Neural network research slowed until computers achieved greater processing power. Also key later advances was the
- The synapses store parameters called "weights" that manipulate the data in the calculations.
- An ANN is typically defined by three types of parameters:
  
  The interconnection pattern between the different layers of neurons
  
  The learning process for updating the weights of the interconnections
  
  The activation function that converts a neuron's weighted input to its output activation.
- nonlinear weighted sum
- Networks such as the previous one are commonly called feedforward, because their graph is a directed acyclic graph. Networks with cycles are commonly called recurrent. Such networks are commonly depicted in the manner shown at the top of the figure, where $\scriptstyle f$ is shown as being dependent upon itself. However, an implied temporal dependence is not shown.
- no solution has a cost less than the cost of the optimal solution
- Learning algorithms search through the solution space to find a function that has the smallest possible cost.
- There are three major learning paradigms, each corresponding to a particular abstract learning task. These are supervised learning, unsupervised learning and reinforcement learning.
- infer the mapping implied by the data; the cost function is related to the mismatch between our mapping and the data and it implicitly contains prior knowledge about the problem domain.
- Tasks that fall within the paradigm of supervised learning are pattern recognition (also known as classification) and regression (also known as function approximation). The supervised learning paradigm is also applicable to sequential data (e.g., for speech and gesture recognition). This can be thought of as learning with a "teacher," in the form of a function that provides continuous feedback on the quality of solutions obtained thus far.
- n unsupervised learning, some data $\scriptstyle x$ is given and the cost function to be minimized, that can be any function of the data $\scriptstyle x$ and the network's output, $\scriptstyle f$ .
16 more annotations...
06 Dec 14

lily yu
- re capable of approximating non-linear functions of their inputs
- the MNIST handwritten digits problem of Yann LeCun and colleagues at NYU.
- data $\scriptstyle x$ are usually not given
- arbitrary function approximation mechanism
- used to diagnose several cancer
- a large diversity of training for real-world operatio
- processing and storage resources
- create a successful net without understanding how it worked
6 more annotations...
29 Oct 14

vkep4eto
25 Aug 14

yanndebray
image processing pattern recognition data mining machine learning wikipedia
10 Aug 14

sapitron
14 Jun 14

camacazze
- are capable of approximating non-linear functions of their inputs.
03 Apr 14

Pauli Haarnimo
Unsorted Bookmarks
10 Feb 14

fair read
- computational models inspired by animals' central nervous systems (in particular the brain) that are capable of machine learning and pattern recognition.
- onsist of sets of adaptive weights
- re capable of approximating non-linear functions of their inputs
1 more annotation...
03 Feb 14

tammyjhaynes
neuralnetworks ann
10 Nov 13

Nav Khare
- The word network in the term 'artificial neural network' refers to the inter–connections between the neurons in the different layers of each system. An example system has three layers. The first layer has input neurons, which send data via synapses to the second layer of neurons, and then via more synapses to the third layer of output neurons
- The synapses store parameters called "weights" that manipulate the data in the calculations.
- An ANN is typically defined by three types of parameters:
  
  The interconnection pattern between different layers of neurons
  
  The learning process for updating the weights of the interconnections
  
  The activation function that converts a neuron's weighted input to its output activation.
- What has attracted the most interest in neural networks is the possibility of learning. Given a specific task to solve, and a class of functions $\scriptstyle F$ , learning means using a set of observations to find $\scriptstyle f^{*} \in F$ which solves the task in some optimal sense.
- This entails defining a cost function $\scriptstyle C : F \rightarrow \mathbb{R}$ such that, for the optimal solution $\scriptstyle f^*$ , $\scriptstyle C(f^*) \leq C(f)$ $\scriptstyle \forall f \in F$ – i.e., no solution has a cost less than the cost of the optimal solution (see Mathematical optimization).
  
  The cost function $\scriptstyle C$ is an important concept in learning, as it is a measure of how far away a particular solution is from an optimal solution to the problem to be solved. Learning algorithms search through the solution space to find a function that has the smallest possible cost.
- There are three major learning paradigm, each corresponding to a particular abstract learning task. These are supervised learning, unsupervised learning and reinforcement learning.
- In supervised learning, we are given a set of example pairs $\scriptstyle (x, y), x \in X, y \in Y$ and the aim is to find a function $\scriptstyle f : X \rightarrow Y$ in the allowed class of functions that matches the examples. In other words, we wish to infer the mapping implied by the data;
- Tasks that fall within the paradigm of supervised learning are pattern recognition (also known as classification) and regression (also known as function approximation
- This can be thought of as learning with a "teacher," in the form of a function that provides continuous feedback on the quality of solutions obtained thus far.
- In unsupervised learning, some data $\scriptstyle x$ is given and the cost function to be minimized, that can be any function of the data $\scriptstyle x$ and the network's output, $\scriptstyle f$ .
- In reinforcement learning, data $\scriptstyle x$ are usually not given, but generated by an agent's interactions with the environment. At each point in time $\scriptstyle t$ , the agent performs an action $\scriptstyle y_t$ and the environment generates an observation $\scriptstyle x_t$ and an instantaneous cost $\scriptstyle c_t$ , according to some (usually unknown) dynamics. The aim is to discover a policy for selecting actions that minimizes some measure of a long-term cost
9 more annotations...
07 Nov 13

Pier Giuseppe Rossi
""Neural network" redirects here. For networks of living neurons, see Biological neural network. For the journal, see Neural Networks (journal)."

rete neurale
31 Oct 13

Jacob Rosen
- re usually unknown, but can be estimated.
  
  More formally, the environment is modeled as a Markov decision process (MDP) with states $\scriptstyle {s_1,...,s_n}\in S$
- Training a neural network model essentially means selecting one model from the set of allowed models (or, in a Bayesian framework, determining a distribution over the set of allowed models) that minimizes the cost criterio
- odel: This will depend on the data representation and the application. Overly complex models tend to lead to problems with learning.
  
  Learning algorithm: There are numerous trade-offs between learning algorithm
1 more annotation...
25 Oct 13

marcella marcelli
- computational models inspired by animal central nervous systems (in particular the brain) that are capable of machine learning and pattern recognition
07 Oct 13

qiongwang
"l"

machine learning
30 Sep 13

Fake Blood
- Artificial neural network
03 Sep 13

Chris Jeffries
ENG 1020
08 Apr 13

gregory333
- nts exhibiting
16 Jan 13

Jordan Alexander
Neural Network
12 Dec 12

akpolatcem
- The word network in the term 'artificial neural network' refers to the inter–connections between the neurons in the different layers of each system. An example system has three layers. The first layer has input neurons, which send data via synapses to the second layer of neurons, and then via more synapses to the third layer of output neurons. More complex systems will have more layers of neurons with some having increased layers of input neurons and output neurons. The synapses store parameters called "weights" that manipulate the data in the calculations.
- An ANN is typically defined by three types of parameters:
  
  The interconnection pattern between different layers of neurons
  
  The learning process for updating the weights of the interconnections
  
  The activation function that converts a neuron's weighted input to its output activation.
17 Nov 12

Neil Mehta
- rtificial neural networks are used with algorithms designed to alter the strength of the connections in the network to produce a desired signal flow.
- functions are performed collectively and in parallel by the units,
- Historically, the use of neural networks models marked a paradigm shift in the late eighties from high-level (symbolic) artificial intelligence, characterized by expert systems with knowledge embodied in if-then rules, to low-level (sub-symbolic) machine learning, characterized by knowledge embodied in the parameters of a dynamical system.
1 more annotation...
04 Oct 12

mingjin207
- A neural network consists of an interconnected group of artificial neurons, and it processes information using a connectionist approach to computation
- The word network in the term 'artificial neural network' refers to the inter–connections between the neurons in the different layers of each system.
- The synapses store parameters called "weights" that manipulate the data in the calculations.
- The cost function $\scriptstyle C$ is an important concept in learning, as it is a measure of how far away a particular solution is from an optimal solution to the problem to be solved.
- the cost must necessarily be a function of the observations
- in a probabilistic formulation the posterior probability of the model can be used as an inverse cost
- to find a function $\scriptstyle f : X \rightarrow Y$ in the allowed class of functions that matches the examples.
- When one tries to minimize this cost using gradient descent for the class of neural networks called multilayer perceptrons, one obtains the common and well-known backpropagation algorithm for training neural networks.
- pattern recognition (also known as classification) and regression (also known as function approximation).
- This can be thought of as learning with a "teacher," in the form of a function that provides continuous feedback on the quality of solutions obtained thus far.
- the posterior probability of the model given the data.
- in general estimation problems; the applications include clustering, the estimation of statistical distributions, compression and filtering.
- In reinforcement learning, data $\scriptstyle x$ are usually not given, but generated by an agent's interactions with the environment.
- to discover a policy for selecting actions that minimizes some measure of a long-term cost; i.e., the expected cumulative cost.
- a policy is defined as conditional distribution over actions given the observations.
- Evolutionary methods,^[3] simulated annealing,^[4] expectation-maximization, non-parametric methods and particle swarm optimization^[5] are some commonly used methods for training neural networks.
- The utility of artificial neural network models lies in the fact that they can be used to infer a function from observations.
- 'capacity', which roughly corresponds to their ability to model any given function.
- This arises in convoluted or over-specified systems when the capacity of the network significantly exceeds the needed free parameters.
- the regularization can be performed by selecting a larger prior probability over simpler models
- to minimize over two quantities: the 'empirical risk' and the 'structural risk', which roughly corresponds to the error over the training set and the predicted error in unseen data due to overfitting.
19 more annotations...
09 Aug 12

katiemdaly
neuralnetworks ai networks programming
Francisco Gomes
leitura_urgente
15 Jun 12

etherington
- largely abandoned for a more practical approach based on statistics and signal processing
02 Jun 12

ubaldo00
- infer a function
- observations
- models
- utility
- function
- ata or task
- impractical
- design
- complexity
- broad categories
- control
- system identification
- quantum chemistry
- Application areas
- game-playing
- pattern recognition
- spam filtering
- several cancers
- diagnose
- behavioral modeling
- cognitive
- theory
- rocesses
- observed
- Biophysical models
- computational algorithms
- biophysical simulation
- neuromorphic computing
- unction approximato
- valued
- rational
- finite numbe
- full powe
- linear connections
- neurons
- super-Turing power
- notion of complexity
- generalizes
- schools of though
- resence of overtraining
- emerges naturall
- form of regularization
- (Bayesian) framework
- larger prior probability
- simpler models
- large diversity of training
- robotics
- extrapolating
- training diversity
- preserving
- overtrained
- esponses
- wide variety
- columnist
- toy problems
- do solve
- genera
- roblem-solving tool
- storage resources
- committed
- processing
- cost of tim
- monetary efficiency
- diverse tasks
- flying aircraft^[
- solve many complex
- detecting
- card fraud
- neural networks
- symbolic approaches
- hybrid models
69 more annotations...
10 Apr 12

Janos Haits
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.

neuralnetworks ai ann intelligence artificial
23 Feb 12

georgesand42
- 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.
- 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.
- 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.
- 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.
- They are usually used to model complex relationships between inputs and outputs or to find patterns in data.
- In modern software implementations of artificial neural networks, the approach inspired by biology has been largely abandoned for a more practical approach based on statistics and signal processing.
- While the more general approach of such adaptive systems is more suitable for real-world problem solving, it has far less to do with the traditional artificial intelligence connectionist models. What they do have in common, however, is the principle of non-linear, distributed, parallel and local processing and adaptation.
- Neural network models in artificial intelligence are usually referred to as artificial neural networks (ANNs); these are essentially simple mathematical models defining a function $\scriptstyle f : X \rightarrow Y$ or a distribution over $\scriptstyle X$ or both $\scriptstyle X$ and $\scriptstyle Y$ , but sometimes models are also intimately associated with a particular learning algorithm or learning rule. A common use of the phrase ANN model really means the definition of a class of such functions (where members of the class are obtained by varying parameters, connection weights, or specifics of the architecture such as the number of neurons or their connectivity).
- [edit] Learning
  
  What has attracted the most interest in neural networks is the possibility of learning. Given a specific task to solve, and a class of functions $\scriptstyle F$ , learning means using a set of observations to find $\scriptstyle f^* \in F$ which solves the task in some optimal sense.
- This entails defining a cost function $\scriptstyle C : F \rightarrow \mathbb{R}$ such that, for the optimal solution $\scriptstyle f^*$ , $\scriptstyle C(f^*) \leq C(f)$ $\scriptstyle \forall f \in F$ (i.e., no solution has a cost less than the cost of the optimal solution).
- The cost function $\scriptstyle C$ is an important concept in learning, as it is a measure of how far away a particular solution is from an optimal solution to the problem to be solved. Learning algorithms search through the solution space to find a function that has the smallest possible cost.
- [edit] Supervised learning
  
  In supervised learning, we are given a set of example pairs $\scriptstyle (x, y), x \in X, y \in Y$ and the aim is to find a function $\scriptstyle f : X \rightarrow Y$ in the allowed class of functions that matches the examples. In other words, we wish to infer the mapping implied by the data; the cost function is related to the mismatch between our mapping and the data and it implicitly contains prior knowledge about the problem domain.
- [edit] Unsupervised learning
  
  In unsupervised learning, some data $\scriptstyle x$ is given and the cost function to be minimized, that can be any function of the data $\scriptstyle x$ and the network's output, $\scriptstyle f$ .
- Reinforcement learning
- In reinforcement learning, data $\scriptstyle x$ are usually not given, but generated by an agent's interactions with the environment. At each point in time $\scriptstyle t$ , the agent performs an action $\scriptstyle y_t$ and the environment generates an observation $\scriptstyle x_t$ and an instantaneous cost $\scriptstyle c_t$ , according to some (usually unknown) dynamics
- formally, the environment is modeled as a Markov decision process (MDP) with states $\scriptstyle {s_1,...,s_n}\in S$ and actions $\scriptstyle {a_1,...,a_m} \in A$ with the following probability distributions:
- [edit] Learning algorithms
  
  Training a neural network model essentially means selecting one model from the set of allowed models (or, in a Bayesian framework, determining a distribution over the set of allowed models) that minimizes the cost criterion. There are numerous algorithms available for training neural network models; most of them can be viewed as a straightforward application of optimization theory and statistical estimation.
- Perhaps the greatest advantage of ANNs is their ability to be used as an arbitrary function approximation mechanism that 'learns' from observed data. However, using them is not so straightforward and a relatively good understanding of the underlying theory is essential.
- The utility of artificial neural network models lies in the fact that they can be used to infer a function from observations. This is particularly useful in applications where the complexity of the data or task makes the design of such a function by hand impractical.
  
  [edit] Real-life applications
  
  The tasks artificial neural networks are applied to tend to fall within the following broad categories:
  
  Function approximation, or regression analysis, including time series prediction, fitness approximation and modeling.
  
  Classification, including pattern and sequence recognition, novelty detection and sequential decision making.
  
  Data processing, including filtering, clustering, blind source separation and compression.
  
  Robotics, including directing manipulators, Computer numerical control.
  
  Application areas include system identification and control (vehicle control, process control, natural resources management), quantum chemistry,^[6] game-playing and decision making (backgammon, chess, poker), pattern recognition (radar systems, face identification, object recognition and more), sequence recognition (gesture, speech, handwritten text recognition), medical diagnosis, financial applications (automated trading systems), data mining (or knowledge discovery in databases, "KDD"), visualization and e-mail spam filtering.
17 more annotations...
30 Nov 11

Marc-Alexandre Gagnon
neuralnetworks ai wikipedia artificial ann
- 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.
13 Oct 11

tlarevo
ict
16 Mar 11

dezfoulianh
- Reinforcement learning
  
  In reinforcement learning, data $\scriptstyle x$ are usually not given, but generated by an agent's interactions with the environment. At each point in time $\scriptstyle t$ , the agent performs an action $\scriptstyle y_t$ and the environment generates an observation $\scriptstyle x_t$ and an instantaneous cost $\scriptstyle c_t$ , according to some (usually unknown) dynamics. The aim is to discover a policy for selecting actions that minimizes some measure of a long-term cost; i.e., the expected cumulative cost. The environment's dynamics and the long-term cost for each policy are usually unknown, but can be estimated.
  
  More formally, the environment is modeled as a Markov decision process (MDP) with states $\scriptstyle {s_1,...,s_n}\in S$ and actions $\scriptstyle {a_1,...,a_m} \in A$ with the following probability distributions: the instantaneous cost distribution $\scriptstyle P(c_t|s_t)$ , the observation distribution $\scriptstyle P(x_t|s_t)$ and the transition $\scriptstyle P(s_{t+1}|s_t, a_t)$ , while a policy is defined as conditional distribution over actions given the observations. Taken together, the two define a Markov chain (MC). The aim is to discover the policy that minimizes the cost; i.e., the MC for which the cost is minimal.
  
  ANNs are frequently used in reinforcement learning as part of the overall algorithm.
  
  Tasks that fall within the paradigm of reinforcement learning are control problems, games and other sequential decision making tasks.
  
  See also: dynamic programming and stochastic control
09 Jan 11

D C
ai neuralnetworks wikipedia Neural_Network toread
05 Jun 10

Kevin Lhoste
project_neurons
06 May 10

Chris Verhaegen
neural network NLP IBW
14 Apr 10

utsuk srivastava
- 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.
- network of simple processing elements (neurons), which can exhibit complex global behavior, determined by the connections between the processing elements and element parameters.
- These networks are also similar to the biological neural networks in the sense that functions are performed collectively and in parallel by the units, rather than there being a clear delineation of subtasks to which various units are assigned (see also connectionism)
1 more annotation...
14 Nov 09

Ching Yi Chan
artificial neural-network
11 Nov 09

Yan Wu
ann 人工神经网络 Wikipedia
08 Sep 09

m m
neuralnetworks
08 Jul 09

quintoelefante
06 Jun 09

Rob Snell
neuralnetworks delicious
12 Feb 09

bassel mar
nn
27 Jan 09

isaac Mao
27 Oct 08

Mario Cosic
wikipedia science ai
22 Aug 08

evgeny yauhenio
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.

In more practical terms 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.

ai artificial intelligence brains brain neurons networks connectionism
08 Apr 08

snichrd
Model Gian recc'd for prediction. Possible ASNN looks relevant for its collectiveness.

horse_racing neuralnetworks
01 Apr 08

Ryan Woodings
algorithm development
22 Feb 08

tonticologo
BRUTUS
08 Feb 08

Milan Stankovic
neural networks
22 Jan 08

Antonia Haller
- Artificial neural network
15 Jan 08

olorin15
Classification
23 Dec 07

avcqgjw
Uncategorized
11 Oct 07

boxofbox
read_me
19 Sep 07

danielrmz
ai
14 Aug 07

ambienthack
ai neuralnetworks
04 May 07

Laszlo Toth
ai_neural_network
28 Apr 07

Dante-Gabryell Monson
Wikipedia Processing Knowledge Cognitive ArtificialIntelligence
06 Sep 06

Adam Kraut
Neural_Networks ai neuralnetworks ann wikipedia programming neural