酷兔英语
    当前位置:
  1. 首页
  2. 文章
  3. 英语能力
  4. 英语词汇
  5. 分类词汇
  6. 正文

机器学习词典(The Machine Learning Dictionary)1

0 收藏 0 分享 0 赞

章节正文

A

 

activation level
The activation level of a neuron in an artificial neural network is a real number often limited to the range 0 to 1, or –1 to 1. In the case of an input neuron the value is obtained externally to the network. In the case of a hidden neuron or output neuron the value is obtained from the neuron's activation function. The activation of a neuron is sometimes thought of as corresponding to the average firing rate of a biological neuron.
activation function
In neural networks, an activation function is the function that describes the output behaviour of a neuron. Most network architectures start by computing the weighted sum of the inputs (that is, the sum of the product of each input with the weight associated with that input. This quantity, the total net input is then usually transformed in some way, using what is sometimes called a squashing function. The simplest squashing function is a step function: if the total net input is less than 0 (or more generally, less than some threshold T) then the output of the neuron is 0, otherwise it is 1. A common squashing function is the logistic function.

In summary, the activation function is the result of applying a squashing function to the total net input.

Aq
A propositional learning system, developed by Michalski.

 

asynchronous vs synchronous
When a neural network is viewed as a collection of connected computation devices, the question arises whether the nodes/devices share a common clock, so that they all perform their computations ("fire") at the same time, (i.e. synchronously) or whether they fire at different times, e.g. they may fire equally often on average, but in a randomsequence (i.e. asynchronously). In the simplest meaningful case, there are two processing nodes, each connected to the other, as shown below.

 

In the asynchronous case, if the yellow node fires first, then it uses the then current value of its input from the red node to determine its output in time step 2, and the red node, if it fires next, will use the updated output from the yellow node to compute its new output in time step 3. In summary, the output values of the red and yellow nodes in time step 3 depend on the outputs of the yellow and red nodes in time steps 2 and 1, respectively.

In the synchronous case, each node obtains the current output of the other node at the same time, and uses the value obtained to compute its new output (in time step 2). In summary, the output values of the red and yellow nodes in time step 2 depend on the outputs of the yellow and red nodes in time step 1. This can produce a different result from the asynchronous method.

Some neural network algorithms are firmly tied to synchronous updates, and some can be operated in either mode. Biological neurons normally fire asynchronously.

attributes
An attribute is a property of an instance that may be used to determine its classification. For example, when classifying objects into different types in a robotic vision task, the size and shape of an instance may be appropriate attributes. Determining useful attributes that can be reasonably calculated may be a difficult job - for example, what attributes of an arbitrary chess end-game position would you use to decide who can win the game? This particular attributeselection problem has been solved, but with considerable effort and difficulty.

Attributes are sometimes also called features.

axon
The axon is the "output" part of a biological neuron. When a neuron fires, a pulse of electrical activity flows along the axon. Towards its end, or ends, the axon splits into a tree. The ends of the axon come into close contact with the dendrites of other neurons. These junctions are termed synapses. Axons may be short (a couple of millimetres) or long (e.g. the axons of the nerves that run down the legs of a reasonably large animal.)

 

B

 

backed-up error estimate
In decision tree pruning one of the issues in deciding whether to prune a branch of the tree is whether the estimated error in classification is greater if the branch is present or pruned. To estimate the error if the branch is present, one takes the estimated errors associated with the children of the branch nodes (which of course must have been previously computed), multiplies them by the estimated frequencies that the current branch will classify data to each child node, and adds up the resulting products. The frequencies are estimated from the numbers of training data instances that are classified as belonging to each child node. This sum is called the backed-up error estimate for the branch node. (The concept of a backed-up error estimate does not make sense for a leaf node.)

See also expected error estimate.

backward pass in backpropagation
The phase of the error backpropagation learning algorithm when the weights are updated, using the delta rule or some modification of it.

The backward pass starts at the output layer of the feedforward network, and updates the incoming weights to units in that layer using the delta rule. Then it works backward, starting with the penultimate layer (last hidden layer), updating the incoming weights to those layers.

Statistics collected during the forward pass are used during the backward pass in updating the weights.

backpropagation or backprop
see error backpropagation
bias
In feedforward and some other neural networks, each hidden unit and each output unit is connected via a trainable weight to a unit (the bias unit) that always has an activation level of –1.

This has the effect of giving each hidden or output a trainable threshold, equal to the value of the weight from the bias unit to the unit.

biological neuron

This is a very much simplified diagram of a biological neuron. Biological neurons come in a variety of types. There is a lot of further structure and physiology that could be considered. The features of a neuron shown above are those of most interest for those constructing artificial neural networks (other than spiking-neuron-based models, and those relying on synchronous activation, such as the Shastri and Ajjanagadde model: see L.Shastri and V. Ajjanagadde: Behavioral and Brain Sciences (1993) 16, 417-494).

However, from the artificial neural network point of view, a biological neuron operates as follows: electrical pulses from other neurons cause the transfer of substances called neurotransmitters (of which there are several varieties) from the synaptic terminals of a neuron's axon (think "output") across a structure called a synapse to the dendrites of other neurons (call them downstream neurons). The arrival of the neurotransmitter in the dendrite of the downstream neuron increases the tendency of the downstream neuron to send an electrical pulse itself ("fire"). If enough dendrites of a neuron receive neurotransmitters in a short enough period of time, the neuron will fire.

Caveat: neurotransmitter substances may be excitatory or inhibitory. The text above assumes that only excitatory neurotransmitters are involved. Inhibitory neurotransmitters, as the name suggests, reduce the tendency of a neuron to fire. Some neurons have a mixture of excitatory synapses and inhibitory synapses (i.e. synapses using inhibitory neurotransmitters) and will only fire if there is enough additional excitatory input to overcome the effect of the inhibitory synapses.

C



文章标签:词典  

章节正文
Copyright © 2023 Qeto All rights reserved.
商务合作 | 联系我们 | 关于我们 | 版权声明 | 隐私条款 | 如果智培

京ICP备05059198号-1 京公网安备 11011202003401号