Machine Learning Data Mining: Problems
Machine Learning Data Mining: Problems
data mining
Problems[show]
Supervised learning
(classification • regression)
[show]
Clustering[show]
Dimensionality reduction[show]
Structured prediction[show]
Anomaly detection[show]
Neural nets[show]
Reinforcement learning[show]
Theory[show]
Machine-learning venues[show]
Related articles[show]
v
t
e
An artificial neural network is an interconnected group of nodes, akin to the vast network of neurons in
a brain. Here, each circular node represents an artificial neuron and an arrow represents a connection from
the output of one artificial neuron to the input of another.
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 isn't 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, e.g., that they
have fur, tails, whiskers and cat-like faces. Instead, they automatically generate identifying
characteristics from the learning material that they process.
An ANN is based on a collection of connected units or nodes called artificial neurons, which
loosely model the neurons in a biological brain. Each connection, like the synapses in a
biological brain, can transmit a signal from one artificial neuron to another. An artificial neuron
that receives a signal can process it and then signal additional artificial neurons connected to it.
In common ANN implementations, the signal at a connection between artificial neurons is a real
number, and the output of each artificial neuron is computed by some non-linear function of the
sum of its inputs. The connections between artificial neurons are called 'edges'. Artificial neurons
and edges typically have a weight that adjusts as learning proceeds. The weight increases or
decreases the strength of the signal at a connection. Artificial neurons may have a threshold
such that the signal is only sent if the aggregate signal crosses that threshold. Typically, artificial
neurons are aggregated into layers. Different layers may perform different kinds of
transformations on their inputs. Signals travel from the first layer (the input layer), to the last layer
(the output layer), possibly after traversing the layers multiple times.
The original goal of the ANN approach was to solve problems in the same way that a human
brain would. However, over time, attention moved to performing specific tasks, leading to
deviations from biology. Artificial neural networks have been used on a variety of tasks,
including computer vision, speech recognition, machine translation, social
network filtering, playing board and video games and medical diagnosis.
Contents
1History
o 1.1Hebbian learning
o 1.2Backpropagation
o 1.3Hardware-based designs
o 1.4Contests
o 1.5Convolutional networks
2Models
o 2.1Components of an artificial neural network
o 2.2Neural networks as functions
o 2.3Learning
o 2.4Learning paradigms
o 2.5Learning algorithms
3Variants
o 3.1Group method of data handling
o 3.2Convolutional neural networks
o 3.3Long short-term memory
o 3.4Deep reservoir computing
o 3.5Deep belief networks
o 3.6Large memory storage and retrieval neural networks
o 3.7Stacked (de-noising) auto-encoders
o 3.8Deep stacking networks
o 3.9Tensor deep stacking networks
o 3.10Spike-and-slab RBMs
o 3.11Compound hierarchical-deep models
o 3.12Deep predictive coding networks
o 3.13Networks with separate memory structures
o 3.14Multilayer kernel machine
4Neural architecture search
5Use
6Applications
o 6.1Types of models
7Theoretical properties
o 7.1Computational power
o 7.2Capacity
o 7.3Convergence
o 7.4Generalization and statistics
8Criticism
o 8.1Training issues
o 8.2Theoretical issues
o 8.3Hardware issues
o 8.4Practical counterexamples to criticisms
o 8.5Hybrid approaches
9Types
10Gallery
11See also
12References
13Bibliography
14External links
History[edit]
Warren McCulloch and Walter Pitts[3] (1943) created a computational model for neural networks
based on mathematics and algorithms called threshold logic. This model paved the way for
neural network research to split into two approaches. One approach focused on biological
processes in the brain while the other focused on the application of neural networks to artificial
intelligence. This work led to work on nerve networks and their link to finite automata.[4]
Hebbian learning[edit]
In the late 1940s, D. O. Hebb[5] created a learning hypothesis based on the mechanism of neural
plasticity that became known as Hebbian learning. Hebbian learning is unsupervised learning.
This evolved into models for long term potentiation. Researchers started applying these ideas to
computational models in 1948 with Turing's B-type machines.
Farley and Clark[6] (1954) first used computational machines, then called "calculators", to
simulate a Hebbian network. Other neural network computational machines were created
by Rochester, Holland, Habit and Duda (1956).[7]
Rosenblatt[8] (1958) created the perceptron, an algorithm for pattern recognition. With
mathematical notation, Rosenblatt described circuitry not in the basic perceptron, such as
the exclusive-or circuit that could not be processed by neural networks at the time.[9]
In 1959, a biological model proposed by Nobel laureates Hubel and Wiesel was based on their
discovery of two types of cells in the primary visual cortex: simple cells and complex cells.[10]
The first functional networks with many layers were published by Ivakhnenko and Lapa in 1965,
becoming the Group Method of Data Handling.[11][12][13]
Neural network research stagnated after machine learning research
by Minsky and Papert (1969),[14] who discovered two key issues with the computational machines
that processed neural networks. The first was that basic perceptrons were incapable of
processing the exclusive-or circuit. The second was that computers didn't have enough
processing power to effectively handle the work required by large neural networks. Neural
network research slowed until computers achieved far greater processing power.
Much of artificial intelligence had focused on high-level (symbolic) models that are processed by
using algorithms, characterized for example by expert systems with knowledge embodied in if-
then rules, until in the late 1980s research expanded to low-level (sub-symbolic) machine
learning, characterized by knowledge embodied in the parameters of a cognitive model.[citation needed]
Backpropagation[edit]
A key trigger for renewed interest in neural networks and learning was Werbos's
(1975) backpropagation algorithm that effectively solved the exclusive-or problem by making the
training of multi-layer networks feasible and efficient. Backpropagation distributed the error term
back up through the layers, by modifying the weights at each node.[9]
In the mid-1980s, parallel distributed processing became popular under the
name connectionism. Rumelhart and McClelland (1986) described the use of connectionism to
simulate neural processes.[15]
Support vector machines and other, much simpler methods such as linear classifiers gradually
overtook neural networks in machine learning popularity. However, using neural networks
transformed some domains, such as the prediction of protein structures.[16][17]
In 1992, max-pooling was introduced to help with least shift invariance and tolerance to
deformation to aid in 3D object recognition.[18][19][20] In 2010, Backpropagation training
through max-pooling was accelerated by GPUs and shown to perform better than other pooling
variants.[21]
The vanishing gradient problem affects many-layered feedforward networks that used
backpropagation and also recurrent neural networks (RNNs).[22][23] As errors propagate from layer
to layer, they shrink exponentially with the number of layers, impeding the tuning of neuron
weights that is based on those errors, particularly affecting deep networks.
To overcome this problem, Schmidhuber adopted a multi-level hierarchy of networks (1992) pre-
trained one level at a time by unsupervised learning and fine-tuned
by backpropagation.[24] Behnke (2003) relied only on the sign of the gradient (Rprop)[25] on
problems such as image reconstruction and face localization.
Hinton et al. (2006) proposed learning a high-level representation using successive layers of
binary or real-valued latent variables with a restricted Boltzmann machine[26] to model each layer.
Once sufficiently many layers have been learned, the deep architecture may be used as
a generative model by reproducing the data when sampling down the model (an "ancestral
pass") from the top level feature activations.[27][28] In 2012, Ng and Dean created a network that
learned to recognize higher-level concepts, such as cats, only from watching unlabeled images
taken from YouTube videos.[29]
Earlier challenges in training deep neural networks were successfully addressed with methods
such as unsupervised pre-training, while available computing power increased through the use
of GPUs and distributed computing. Neural networks were deployed on a large scale, particularly
in image and visual recognition problems. This became known as "deep learning".[citation needed]
Hardware-based designs[edit]
Computational devices were created in CMOS, for both biophysical simulation and neuromorphic
computing. Nanodevices[30] for very large scale principal components analyses
and convolution may create a new class of neural computing because they are
fundamentally analog rather than digital (even though the first implementations may use digital
devices).[31] Ciresan and colleagues (2010)[32] in Schmidhuber's group showed that despite the
vanishing gradient problem, GPUs makes back-propagation feasible for many-layered
feedforward neural networks.
Contests[edit]
Between 2009 and 2012, recurrent neural networks and deep feedforward neural networks
developed in Schmidhuber's research group won eight international competitions in pattern
recognition and machine learning.[33][34] For example, the bi-directional and multi-dimensional long
short-term memory (LSTM)[35][36][37][38] of Graves et al. won three competitions in connected
handwriting recognition at the 2009 International Conference on Document Analysis and
Recognition (ICDAR), without any prior knowledge about the three languages to be learned.[37][36]
Ciresan and colleagues won pattern recognition contests, including the IJCNN 2011 Traffic Sign
Recognition Competition,[39] the ISBI 2012 Segmentation of Neuronal Structures in Electron
Microscopy Stacks challenge[40] and others. Their neural networks were the first pattern
recognizers to achieve human-competitive or even superhuman performance[41] on benchmarks
such as traffic sign recognition (IJCNN 2012), or the MNIST handwritten digits problem.
Researchers demonstrated (2010) that deep neural networks interfaced to a hidden Markov
model with context-dependent states that define the neural network output layer can drastically
reduce errors in large-vocabulary speech recognition tasks such as voice search.
GPU-based implementations[42] of this approach won many pattern recognition contests, including
the IJCNN 2011 Traffic Sign Recognition Competition,[39] the ISBI 2012 Segmentation of neuronal
structures in EM stacks challenge,[40] the ImageNet Competition[43] and others.
Deep, highly nonlinear neural architectures similar to the neocognitron[44] and the "standard
architecture of vision",[45] inspired by simple and complex cells, were pre-trained by unsupervised
methods by Hinton.[46][27] A team from his lab won a 2012 contest sponsored by Merck to design
software to help find molecules that might identify new drugs.[47]
Convolutional networks[edit]
As of 2011, the state of the art in deep learning feedforward networks alternated between
convolutional layers and max-pooling layers,[42][48] topped by several fully or sparsely connected
layers followed by a final classification layer. Learning is usually done without unsupervised pre-
training.
Such supervised deep learning methods were the first to achieve human-competitive
performance on certain tasks.[41]
Artificial neural networks were able to guarantee shift invariance to deal with small and large
natural objects in large cluttered scenes, only when invariance extended beyond shift, to all ANN-
learned concepts, such as location, type (object class label), scale, lighting and others. This was
realized in Developmental Networks (DNs)[49] whose embodiments are Where-What Networks,
WWN-1 (2008)[50] through WWN-7 (2013).[51]
Models[edit]
This section may be confusing or unclear to readers. Please
help us clarify the section. There might be a discussion about this
on the talk page. (April 2017) (Learn how and when to remove this template
message)
Neuron and myelinated axon, with signal flow from inputs at dendrites to outputs at axon terminals
An artificial neural network is a network of simple elements called artificial neurons, which
receive input, change their internal state (activation) according to that input, and produce output
depending on the input and activation.
An artificial neuron mimics the working of a biophysical neuron with inputs and outputs, but is not
a biological neuron model.
The network forms by connecting the output of certain neurons to the input of other neurons
forming a directed, weighted graph. The weights as well as the functions that compute the
activation can be modified by a process called learning which is governed by a learning rule.[52]
A neuron with label receiving an input from predecessor neurons consists of the
following components:[52]
.
Often the output function is simply the Identity function.
An input neuron has no predecessor but serves as input interface for the whole network.
Similarly an output neuron has no successor and thus serves as output interface of the
whole network.
Connections, weights and biases[edit]
The network consists of connections, each connection transferring the output of a
The propagation function computes the input to the neuron from the
.
When a bias value added with the function, the above form changes to following [54]
, where is a bias.
Learning rule[edit]
The learning rule is a rule or an algorithm which modifies the parameters of the
neural network, in order for a given input to the network to produce a favored
output. This learningprocess typically amounts to modifying the weights and
thresholds of the variables within the network.[52]
other functions , that can further be decomposed into other functions. This
can be conveniently represented as a network structure, with arrows depicting
the dependencies between functions. A widely used type of composition is
a vector .
The first view is the functional view: the input is transformed into a 3-
The second view is the probabilistic view: the random variable depends
upon the random variable . This view is most commonly encountered in the
context of graphical models.
The two views are largely equivalent. In either case, for this particular
architecture, the components of individual layers are independent of each other
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 is shown as being dependent upon itself.
However, an implied temporal dependence is not shown.
Learning[edit]
See also: Mathematical optimization, Estimation theory, and Machine learning
The possibility of learning has attracted the most interest in neural networks.
using a set of observations to find which solves the task in some optimal
sense.
This entails defining a cost function such that, for the optimal solution
, – i.e., no solution has a cost less than the cost of the optimal
solution (see mathematical optimization).
In practical situations we would only have samples from and thus, for
the above example, we would only minimize . Thus, the cost is minimized
over a sample of the data rather than the entire distribution.
When some form of online machine learning must be used, where the cost
is reduced as each new example is seen. While online machine learning is often
used when is fixed, it is most useful in the case where the distribution
changes slowly over time. In neural network methods, some form of online
machine learning is frequently used for finite datasets.
Choosing a cost function[edit]
While it is possible to define an ad hoc cost function, frequently a particular cost
(function) is used, either because it has desirable properties (such as convexity)
or because it arises naturally from a particular formulation of the problem (e.g.,
in a probabilistic formulation the posterior probability of the model can be used
as an inverse cost). Ultimately, the cost function depends on the task.
Backpropagation[edit]
Main article: Backpropagation
A DNN can be discriminatively trained with the standard backpropagation
algorithm. Backpropagation is a method to calculate the gradient of the loss
function (produces the cost associated with a given state) with respect to the
weights in an ANN.
The basics of continuous backpropagation[11][56][57][58] were derived in the context
of control theory by Kelley[59] in 1960 and by Bryson in 1961,[60] using principles
of dynamic programming. In 1962, Dreyfus published a simpler derivation based
only on the chain rule.[61] Bryson and Ho described it as a multi-stage dynamic
system optimization method in 1969.[62][63] In 1970, Linnainmaa finally published
the general method for automatic differentiation (AD) of discrete connected
networks of nested differentiable functions.[64][65] This corresponds to the modern
version of backpropagation which is efficient even when the networks are
sparse.[11][56][66][67] In 1973, Dreyfus used backpropagation to adapt parameters of
controllers in proportion to error gradients.[68] In 1974, Werbos mentioned the
possibility of applying this principle to Artificial neural networks,[69] and in 1982,
he applied Linnainmaa's AD method to neural networks in the way that is widely
used today.[56][70] In 1986, Rumelhart, Hinton and Williams noted that this method
can generate useful internal representations of incoming data in hidden layers of
neural networks.[71] In 1993, Wan was the first[11] to win an international pattern
recognition contest through backpropagation.[72]
The weight updates of backpropagation can be done via stochastic gradient
descent using the following equation:
Learning paradigms[edit]
The three major learning paradigms each correspond to a particular learning
task. These are supervised learning, unsupervised
learning and reinforcement learning.
Supervised learning[edit]
Supervised learning uses a set of example pairs and the aim is to find
the average squared error between the network's output, , and the
target value over all the example pairs. Minimizing this cost
using gradient descent for the class of neural networks called multilayer
perceptrons (MLP), produces the backpropagation algorithm for training
neural networks.
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 hand writing, 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.
Unsupervised learning[edit]
In unsupervised learning, some data is given and the cost function to
be minimized, that can be any function of the data and the network's
output, .
The cost function is dependent on the task (the model domain) and any a
priori assumptions (the implicit properties of the model, its parameters and
the observed variables).
Learning algorithms[edit]
See also: Machine learning
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.
Numerous algorithms are available for training neural network models; most
of them can be viewed as a straightforward application
of optimization theory and statistical estimation.
Most employ some form of gradient descent, using backpropagation to
compute the actual gradients. This is done by simply taking the derivative of
the cost function with respect to the network parameters and then changing
those parameters in a gradient-related direction. Backpropagation training
algorithms fall into three categories:
Variants[edit]
Group method of data handling[edit]
Main article: Group method of data handling
The Group Method of Data Handling (GMDH)[94] features fully automatic
structural and parametric model optimization. The node activation functions
are Kolmogorov-Gabor polynomials that permit additions and multiplications.
It used a deep feedforward multilayer perceptron with eight layers.[95] It is
a supervised learning network that grows layer by layer, where each layer is
trained by regression analysis. Useless items are detected using a
validation set, and pruned through regularization. The size and depth of the
resulting network depends on the task.[96]
Convolutional neural networks[edit]
Main article: Convolutional neural network
A convolutional neural network (CNN) is a class of deep, feed-forward
networks, composed of one or more convolutional layers with fully
connected layers (matching those in typical Artificial neural networks) on
top. It uses tied weights and pooling layers. In particular, max-pooling[19] is
often structured via Fukushima's convolutional architecture.[97] This
architecture allows CNNs to take advantage of the 2D structure of input
data.
CNNs are suitable for processing visual and other two-dimensional
data.[98][99] They have shown superior results in both image and speech
applications. They can be trained with standard backpropagation. CNNs are
easier to train than other regular, deep, feed-forward neural networks and
have many fewer parameters to estimate.[100] Examples of applications in
computer vision include DeepDream[101] and robot navigation.[102]
A recent development has been that of Capsule Neural Network (CapsNet),
the idea behind which is to add structures called capsules to a CNN and to
reuse output from several of those capsules to form more stable (with
respect to various perturbations) representations for higher order
capsules.[103]
The higher level representations are relatively stable and robust to input
corruption;
It is necessary to extract features that are useful for representation of
the input distribution.
this is the corrupting step. Then the corrupted input passes through a
basic auto-encoder process and is mapped to a hidden representation
Spike-and-slab RBMs[edit]
The need for deep learning with real-valued inputs, as in Gaussian
restricted Boltzmann machines, led to the spike-and-
slab RBM (ssRBM), which models continuous-valued inputs with
strictly binary latent variables.[156] Similar to basic RBMs and its variants,
a spike-and-slab RBM is a bipartite graph, while like GRBMs, the visible
units (input) are real-valued. The difference is in the hidden layer, where
each hidden unit has a binary spike variable and a real-valued slab
variable. A spike is a discrete probability mass at zero, while a slab is
a density over continuous domain;[157] their mixture forms a prior.[158]
An extension of ssRBM called µ-ssRBM provides extra modeling
capacity using additional terms in the energy function. One of these
terms enables the model to form a conditional distribution of the spike
variables by marginalizing out the slab variables given an observation.
of :
Use[edit]
Using Artificial neural networks requires an understanding of
their characteristics.
Types of models[edit]
Many types of models are used, defined at different levels of
abstraction and modeling different aspects of neural systems.
They range from models of the short-term behavior of individual
neurons,[222] models of how the dynamics of neural circuitry arise
from interactions between individual neurons and finally to
models of how behavior can arise from abstract neural modules
that represent complete subsystems. These include models of
the long-term, and short-term plasticity, of neural systems and
their relations to learning and memory from the individual
neuron to the system level.
Theoretical properties[edit]
Computational power[edit]
The multilayer perceptron is a universal function approximator,
as proven by the universal approximation theorem. However,
the proof is not constructive regarding the number of neurons
required, the network topology, the weights and the learning
parameters.
A specific recurrent architecture with rational valued weights (as
opposed to full precision real number-valued weights) has the
full power of a universal Turing machine,[223] using a finite
number of neurons and standard linear connections. Further,
the use of irrational values for weights results in a machine
with super-Turing power.[224]
Capacity[edit]
Models' "capacity" property roughly corresponds to their ability
to model any given function. It is related to the amount of
information that can be stored in the network and to the notion
of complexity.[citation needed]
Convergence[edit]
Models may not consistently converge on a single solution,
firstly because many local minima may exist, depending on the
cost function and the model. Secondly, the optimization method
used might not guarantee to converge when it begins far from
any local minimum. Thirdly, for sufficiently large data or
parameters, some methods become impractical. However,
for CMAC neural network, a recursive least squares algorithm
was introduced to train it, and this algorithm can be guaranteed
to converge in one step.[92]
Criticism[edit]
Training issues[edit]
A common criticism of neural networks, particularly in
robotics, is that they require too much training for real-world
operation.[citation needed] Potential solutions include randomly
shuffling training examples, by using a numerical
optimization algorithm that does not take too large steps
when changing the network connections following an
example and by grouping examples in so-called mini-
batches. Improving the training efficiency and convergence
capability has always been an ongoing research area for
neural network. For example, by introducing a recursive
least squares algorithm for CMAC neural network, the
training process only takes one step to converge.[92]
Theoretical issues[edit]
No neural network has solved computationally difficult
problems such as the n-Queens problem, the travelling
salesman problem, or the problem of factoring large
integers.
A fundamental objection is that they do not reflect how real
neurons function. Back propagation is a critical part of most
artificial neural networks, although no such mechanism
exists in biological neural networks.[225] How information is
coded by real neurons is not known. Sensor
neurons fire action potentials more frequently with sensor
activation and muscle cells pull more strongly when their
associated motor neurons receive action potentials more
frequently.[226] Other than the case of relaying information
from a sensor neuron to a motor neuron, almost nothing of
the principles of how information is handled by biological
neural networks is known.
The motivation behind Artificial neural networks is not
necessarily to strictly replicate neural function, but to use
biological neural networks as an inspiration. A central claim
of Artificial neural networks is therefore that it embodies
some new and powerful general principle for processing
information. Unfortunately, these general principles are ill-
defined. It is often claimed that they are emergent from the
network itself. This allows simple statistical association (the
basic function of artificial neural networks) to be described
as learning or recognition. Alexander Dewdney commented
that, as a result, artificial neural networks have a
"something-for-nothing quality, one that imparts a peculiar
aura of laziness and a distinct lack of curiosity about just
how good these computing systems are. No human hand
(or mind) intervenes; solutions are found as if by magic; and
no one, it seems, has learned anything".[227]
Biological brains use both shallow and deep circuits as
reported by brain anatomy,[228] displaying a wide variety of
invariance. Weng[229] argued that the brain self-wires largely
according to signal statistics and therefore, a serial cascade
cannot catch all major statistical dependencies.
Hardware issues[edit]
Large and effective neural networks require considerable
computing resources.[230] While the brain has hardware
tailored to the task of processing signals through a graph of
neurons, simulating even a simplified neuron on von
Neumann architecture may compel a neural network
designer to fill many millions of database rows for its
connections – which can consume vast amounts
of memory and storage. Furthermore, the designer often
needs to transmit signals through many of these
connections and their associated neurons – which must
often be matched with enormous CPU processing power
and time.
Schmidhuber notes that the resurgence of neural networks
in the twenty-first century is largely attributable to advances
in hardware: from 1991 to 2015, computing power,
especially as delivered by GPGPUs (on GPUs), has
increased around a million-fold, making the standard
backpropagation algorithm feasible for training networks
that are several layers deeper than before.[231] The use of
parallel GPUs can reduce training times from months to
days.[230]
Neuromorphic engineering addresses the hardware
difficulty directly, by constructing non-von-Neumann chips
to directly implement neural networks in circuitry. Another
chip optimized for neural network processing is called
a Tensor Processing Unit, or TPU.[232]
Practical counterexamples to
criticisms[edit]
Arguments against Dewdney's position are that neural
networks have been successfully used to solve many
complex and diverse tasks, ranging from autonomously
flying aircraft[233]to detecting credit card fraud to mastering
the game of Go.
Technology writer Roger Bridgman commented:
Neural networks, for instance, are in the dock not only
because they have been hyped to high heaven, (what
hasn't?) but also because you could create a successful net
without understanding how it worked: the bunch of numbers
that captures its behaviour would in all probability be "an
opaque, unreadable table...valueless as a scientific
resource".
In spite of his emphatic declaration that science is not
technology, Dewdney seems here to pillory neural nets as
bad science when most of those devising them are just
trying to be good engineers. An unreadable table that a
useful machine could read would still be well worth
having.[234]
Although it is true that analyzing what has been learned by
an artificial neural network is difficult, it is much easier to do
so than to analyze what has been learned by a biological
neural network. Furthermore, researchers involved in
exploring learning algorithms for neural networks are
gradually uncovering general principles that allow a learning
machine to be successful. For example, local vs non-local
learning and shallow vs deep architecture.[235]
Hybrid approaches[edit]
Advocates of hybrid models (combining neural networks
and symbolic approaches), claim that such a mixture can
better capture the mechanisms of the human mind.[236][237]
Types[edit]
Main article: Types of artificial neural networks
Artificial neural networks have many variations. The
simplest, static types have one or more static components,
including number of units, number of layers, unit weights
and topology. Dynamic types allow one or more of these to
change during the learning process. The latter are much
more complicated, but can shorten learning periods and
produce better results. Some types allow/require learning to
be "supervised" by the operator, while others operate
independently. Some types operate purely in hardware,
while others are purely software and run on general
purpose computers.