You get a bonus - 1 coin for daily activity. Now you have 1 coin

1.7 Neural networks - Imitation of psychological intuition using artificial

Lecture



Это продолжение увлекательной статьи про имитация психологической интуиции с помощью искусственных нейронных сетей.

...

src="/th/25/blogs/id7106/541b4ddeb8934e798509517d14d92eff.png" data-auto-open loading="lazy" alt="Imitation of psychological intuition using artificial neural networks" > functions) in a situation where the density Imitation of psychological intuition using artificial neural networks unknown, but random and independent sampling of pairs is given Imitation of psychological intuition using artificial neural networks .

1.6. Algorithms and methods of unconditional optimization

As it was shown in the previous paragraph of this chapter, the solution of the main problems of dependency recovery is achieved using the procedure of optimization of the quality functional.

Its solution will be considered in the approaches of the unconditional minimization of a smooth function. Imitation of psychological intuition using artificial neural networks [77].

This task is directly related to the conditions for the existence of an extremum at the point:

- Necessary condition of the first order. Point Imitation of psychological intuition using artificial neural networks called the local minimum Imitation of psychological intuition using artificial neural networks on Imitation of psychological intuition using artificial neural networks if there is Imitation of psychological intuition using artificial neural networks for Imitation of psychological intuition using artificial neural networks . According to the Fermat theorem if Imitation of psychological intuition using artificial neural networks - minimum point Imitation of psychological intuition using artificial neural networks on Imitation of psychological intuition using artificial neural networks and Imitation of psychological intuition using artificial neural networks differentiable in Imitation of psychological intuition using artificial neural networks then Imitation of psychological intuition using artificial neural networks

- A sufficient condition of the first order. If a Imitation of psychological intuition using artificial neural networks - convex function, differentiable at a point Imitation of psychological intuition using artificial neural networks and Imitation of psychological intuition using artificial neural networks then Imitation of psychological intuition using artificial neural networks - global minimum point Imitation of psychological intuition using artificial neural networks on Imitation of psychological intuition using artificial neural networks

- Necessary condition of the second order. If a Imitation of psychological intuition using artificial neural networks - minimum point Imitation of psychological intuition using artificial neural networks on Imitation of psychological intuition using artificial neural networks and Imitation of psychological intuition using artificial neural networks twice differentiable in it then Imitation of psychological intuition using artificial neural networks

— Достаточное условие второго порядка. Если в точке Imitation of psychological intuition using artificial neural networksImitation of psychological intuition using artificial neural networks дважды дифференцируема, выполнено необходимое условие первого порядка ( Imitation of psychological intuition using artificial neural networks ) and Imitation of psychological intuition using artificial neural networks then Imitation of psychological intuition using artificial neural networks — точка локального минимума.

Условия экстремума являются основой, на которой строятся методы решения оптимизационных задач. В ряде случаев условия экстремума хотя и не дают возможности явного нахождения решения, но сообщают много информации об его свойствах.

Кроме того, доказательство условий экстремума или вид этих условий часто указывают путь построения методов оптимизации.

При обосновании методов приходится делать ряд предположений. Обычно при этом требуется, чтобы в точке Imitation of psychological intuition using artificial neural networks выполнялось достаточное условие экстремума. Таким образом, условия экстремума фигурируют в теоремах о сходимости методов.

И, наконец, сами доказательства сходимости обычно строятся на том, что показывается, как «невязка» в условии экстремума стремится к нулю.

При решении оптимизационных задач существенны требования существования, единственности и устойчивости решения.

Существование точки минимума проверяется при помощи теоремы Вейерштрасса:

Let be Imitation of psychological intuition using artificial neural networks непрерывна на Imitation of psychological intuition using artificial neural networks и множество Imitation of psychological intuition using artificial neural networks для некоторого Imitation of psychological intuition using artificial neural networks непусто и ограничено. Тогда существует точка глобального минимума Imitation of psychological intuition using artificial neural networks on Imitation of psychological intuition using artificial neural networks

При анализе единственности точки экстремума применяются следующие рассуждения:

Точка минимума называется локально единственной, если в некоторой ее окрестности нет других локальных минимумов. Считается, что Imitation of psychological intuition using artificial neural networks — невырожденная точка минимума, если в ней выполнено достаточное условие экстремума второго порядка ( Imitation of psychological intuition using artificial neural networks , Imitation of psychological intuition using artificial neural networks ).

Доказано, что точка минимума (строго) выпуклой функции (глобально) единственна.

Проблема устойчивости решения возникает в связи со следующим кругом вопросов:

—– Imitation of psychological intuition using artificial neural networks локального минимума Imitation of psychological intuition using artificial neural networks называется локально устойчивой, если к ней сходится любая локальная минимизирующая последовательность, то есть если найдется Imitation of psychological intuition using artificial neural networks такое, что из Imitation of psychological intuition using artificial neural networks follows Imitation of psychological intuition using artificial neural networks

При обсуждении проблемы устойчивости решения задачи оптимизации можно выделить следующие важные теоремы.

— Точка локального минимума непрерывной функции Imitation of psychological intuition using artificial neural networks локально устойчива тогда и только тогда, когда она локально единственна.

— Пусть Imitation of psychological intuition using artificial neural networks — локально устойчивая точка минимума непрерывной функции Imitation of psychological intuition using artificial neural networks , but Imitation of psychological intuition using artificial neural networks — непрерывная функция. Тогда для достаточно малых Imitation of psychological intuition using artificial neural networks function Imitation of psychological intuition using artificial neural networks имеет локально единственную точку минимума Imitation of psychological intuition using artificial neural networks в окрестности Imitation of psychological intuition using artificial neural networks and Imitation of psychological intuition using artificial neural networks at Imitation of psychological intuition using artificial neural networks

— Пусть Imitation of psychological intuition using artificial neural networks — невырожденная точка минимума Imitation of psychological intuition using artificial neural networks , а функция Imitation of psychological intuition using artificial neural networks непрерывно дифференцируема в окрестности точки Imitation of psychological intuition using artificial neural networks . Тогда для достаточно малых Imitation of psychological intuition using artificial neural networks exists Imitation of psychological intuition using artificial neural networks — локальная точка минимума функции Imitation of psychological intuition using artificial neural networks в окрестности Imitation of psychological intuition using artificial neural networks , and Imitation of psychological intuition using artificial neural networks

Помимо качественной характеристики точки минимума (устойчива она или нет) существенным является вопрос количественной оценки устойчивости. Такие оценки, позволяющие судить о близости точки Imitation of psychological intuition using artificial neural networks к решению Imitation of psychological intuition using artificial neural networks , if a Imitation of psychological intuition using artificial neural networks близко к Imitation of psychological intuition using artificial neural networks записываются следующим образом:

Для сильно выпуклых функций:

Imitation of psychological intuition using artificial neural networks

Where Imitation of psychological intuition using artificial neural networks — константа сильной выпуклости.

Для невырожденной точки минимума:

Imitation of psychological intuition using artificial neural networks

Where Imitation of psychological intuition using artificial neural networks — наименьшее собственное значение матрицы Imitation of psychological intuition using artificial neural networks .

As you can see, in each of these definitions Imitation of psychological intuition using artificial neural networks plays the role of characteristics of the "stability margin" of the minimum point.

Besides Imitation of psychological intuition using artificial neural networks as the characteristics of the stability of the minimum point using the "normalized" indicator Imitation of psychological intuition using artificial neural networks called the conditionality of the minimum point Imitation of psychological intuition using artificial neural networks .

Imitation of psychological intuition using artificial neural networks
Imitation of psychological intuition using artificial neural networks

Can say that Imitation of psychological intuition using artificial neural networks characterizes the degree of elongation level lines Imitation of psychological intuition using artificial neural networks in the surrounding area Imitation of psychological intuition using artificial neural networks - “ravine” function (the more Imitation of psychological intuition using artificial neural networks , the more "ravine" nature of the function).

The most important ideologically the following methods of unconditional optimization: gradient and Newton.

The idea of ​​the gradient method is to reach an extremum by iteratively repeating a procedure of successive approximations starting from the initial approximation. Imitation of psychological intuition using artificial neural networks according to the formula Imitation of psychological intuition using artificial neural networks where Imitation of psychological intuition using artificial neural networks - step length.

The convergence of this method is confirmed in the proof of the following theorem:

Let function Imitation of psychological intuition using artificial neural networks differentiable on Imitation of psychological intuition using artificial neural networks gradient Imitation of psychological intuition using artificial neural networks satisfies the Lipschitz condition:

Imitation of psychological intuition using artificial neural networks ,

Imitation of psychological intuition using artificial neural networks limited to below: Imitation of psychological intuition using artificial neural networks

and Imitation of psychological intuition using artificial neural networks satisfies the condition Imitation of psychological intuition using artificial neural networks

Then in the gradient method with a constant step Imitation of psychological intuition using artificial neural networks gradient tends to 0: Imitation of psychological intuition using artificial neural networks and function Imitation of psychological intuition using artificial neural networks monotonously decreases: Imitation of psychological intuition using artificial neural networks

For strongly convex functions, stronger assertions on the convergence of the gradient method are proved.

When solving the optimization problem by the Newton method, an approach is used which consists in an iterative process of the form

Imitation of psychological intuition using artificial neural networks

and in finding the extremum point as a solution of a system of n equations with n unknowns

Imitation of psychological intuition using artificial neural networks .

In Newton's method, the equations are linearized at Imitation of psychological intuition using artificial neural networks and solution of the linearized form system

Imitation of psychological intuition using artificial neural networks

An analysis of the advantages and disadvantages of iterative optimization methods can be summarized in a table (see Table 3).

Table 3. Advantages and disadvantages of iterative optimization methods

Method Merits disadvantages
Gradient Global convergence, weak requirements for Imitation of psychological intuition using artificial neural networks simplicity of calculations Slow convergence, the need to choose Imitation of psychological intuition using artificial neural networks .
Newton Fast convergence Local convergence, strict requirements for Imitation of psychological intuition using artificial neural networks , a large amount of computation.

It can be seen that the advantages and disadvantages of these methods are mutually complementary, which makes it attractive to create modifications of these methods that combine the advantages of methods and are free from their disadvantages.

The modification of the gradient method is the method of the quickest descent:

Imitation of psychological intuition using artificial neural networks , Imitation of psychological intuition using artificial neural networks

The modification of Newton's method in order to give it the property of global convergence is possible, for example, by adjusting the step length:

Imitation of psychological intuition using artificial neural networks

This method is called Newton's damped method. Possible approaches to the step selection method Imitation of psychological intuition using artificial neural networks :

- Calculation by the formula

Imitation of psychological intuition using artificial neural networks ;

- Iterative algorithm, consisting in the sequential crushing step Imitation of psychological intuition using artificial neural networks on constant Imitation of psychological intuition using artificial neural networks starting with Imitation of psychological intuition using artificial neural networks before the condition

Imitation of psychological intuition using artificial neural networks , Imitation of psychological intuition using artificial neural networks

or conditions Imitation of psychological intuition using artificial neural networks , Imitation of psychological intuition using artificial neural networks

Newton's damped method converges globally for smooth strongly convex functions.

In addition to single-step methods, which include the gradient method and Newton's method, there is a whole class of multi-step methods that use information obtained from previous steps to optimize. These include:

- Imitation of psychological intuition using artificial neural networks where Imitation of psychological intuition using artificial neural networks , Imitation of psychological intuition using artificial neural networks - some parameters. The introduction of inertia motion (member Imitation of psychological intuition using artificial neural networks ) in some cases leads to acceleration of convergence due to the alignment of movement along the “gill-like” relief of the function;

- The conjugate gradient method. Here the optimization parameters are found from the solution of the two-dimensional optimization problem:

Imitation of psychological intuition using artificial neural networks ,
Imitation of psychological intuition using artificial neural networks

In addition to all the above optimization methods, there is also a class of methods based on the idea of ​​restoring the quadratic approximation of a function from the values ​​of its gradients at a number of points. These include:

- Imitation of psychological intuition using artificial neural networks where matrix Imitation of psychological intuition using artificial neural networks recalculated recursively based on information obtained on k- yiteration, so that Imitation of psychological intuition using artificial neural networks . Such methods include DFP (Davidon-Fletcher-Powell method) and BFGS or BFGSH (Broyden-Fletcher-Goldfarb-Shanno method) [46].

- Imitation of psychological intuition using artificial neural networks , Imitation of psychological intuition using artificial neural networks can be considered as gradient in metric Imitation of psychological intuition using artificial neural networks , and the optimal choice of metrics is Imitation of psychological intuition using artificial neural networks .

1.7 Neural networks

In this paper, the problem of pattern recognition and dependency recovery will be solved mainly using neural networks. The review of this topic is based on [1] - [6], [8] - [15], [22], [23], [32] - [34], [36] - [41], [59], [ 64], [67] - [70], [83] - [88].

1.7.1 Basic Elements

The neural network is a structure of interconnected cellular automata, consisting of the following main elements:

A neuron is an element that converts an input signal by function:

Imitation of psychological intuition using artificial neural networks

where x is the input signal, c is the parameter that determines the steepness of the graph of the threshold function, and c m is the parameter of spontaneous neuron activity.

Adder - an element that performs the summation of signals arriving at its input:

Imitation of psychological intuition using artificial neural networks

A synapse is an element that performs linear signal transmission:

Imitation of psychological intuition using artificial neural networks

where w is the “weight” of the corresponding synapse.

1.7.2 Structure of the neural network

The network consists of neurons connected by synapses through adders according to the following scheme:

Imitation of psychological intuition using artificial neural networks

1.7.3 Direct network operation

The network operates discretely in time (clock cycles). Then synapses can be divided into “communication synapses”, which transmit signals in a given clock cycle, and “memory synapses”, which transmit a signal from the output of a neuron to its input at the next clock cycle . The signals arising during the operation of the network are divided into direct (used when the network produces results) and dual (used in training) and can be given by the following formulas:

For the i-th neuron at the time step T:

Imitation of psychological intuition using artificial neural networks

where m i0 is the network initiation parameter, x i1 is the network input signals arriving at this neuron, f iT is the neuron output at the time step T, A i1 is the input parameter of the i-th neuron at the first network operation time, A iT is the input the signal of the i-th neuron at the time step T, a ji is the weight of the synapse from the j-th neuron to the i-th, a Mi is the weight of the synaptic memory of the i-th neuron, a i1 is the neuron parameter and a i2 is the parameter of spontaneous neuron activity, a iT-1 - input i-th neuron in cycle T-1, f jT-1 - the output signal j-th neuron in cycle T-1 and f iT, a - derivative i-th neuron to the input of its persecuted.

For a synapse connection from the i-th neuron to the j-th:

Imitation of psychological intuition using artificial neural networksImitation of psychological intuition using artificial neural networks

where s jT is the input signal of the synapse from the i-th neuron to the j-th, f iT is the output signal of the i-th neuron, a ij is the weight of the given synapse, s ijT is the output signal of the synapse at the time step T.

For the synapse memory i-th neuron: Imitation of psychological intuition using artificial neural networks

1.7.4 Network Training

In this task, the training will take place according to the “connectionist” model, that is, by adjusting the weights of the synapses.

The essence of learning is to minimize the error function. Imitation of psychological intuition using artificial neural networks where W is the synaptic weights map. To solve the minimization problem, it is necessary to calculate the gradient of the function using adjustable parameters:

Imitation of psychological intuition using artificial neural networks

1.7.5 Reverse operation

The gradient is calculated during the countdown of time ticks Imitation of psychological intuition using artificial neural networks according to the following formulas:

For synapse communication:

Imitation of psychological intuition using artificial neural networks

For memory synapse:

Imitation of psychological intuition using artificial neural networks

Finally, after passing the q clock ticks, the partial derivatives on the weights of synapses will have the form for synapses of memory and for synapses of communication, respectively:

Imitation of psychological intuition using artificial neural networks

Conclusions of chapter 1

1. The mathematical apparatus used in psychodiagnostics does not sufficiently meet modern requirements.

2. A pressing need is the introduction of the mathematical apparatus associated with pattern recognition and dependency recovery into psychodiagnostic techniques.

3. The existing mathematical methods and algorithms are too complex and time-consuming for their use by subject specialists, including psychodiagnostics, and do not allow computer techniques to follow the experience of a human specialist directly from precedents.

4. The use of the mathematical apparatus of neural networks when creating neural network expert psychological systems allows minimizing the requirements for the mathematical preparation of their creators.

Chapter 2. Neural networks solving classical problems of psychodiagnostics

2.1 Classic experiment

The specific features of the mathematical apparatus of neural networks, described in detail in [36], [41] and the experience of their application in various fields of knowledge (see, for example, [5], [8], [10], [13], [84], [ 86]) suggested the possibility of solving psychological problems with their help.

It was supposed to test several possibilities of using neural networks, namely:

- Firstly, it was expected to solve a serious problem arising from the developers and users of computer psychological tests, namely the adaptability of methods. The mathematical construction of modern objective diagnostic tests is based on a comparison, comparison of the identified condition with the norm, the standard [21], [71]. However, it is clear that the norms worked out for one sociocultural group are not necessarily the same for another (for example, the difficulties that have to be overcome when adapting foreign methods can be cited). Neural network simulators have a useful feature in this case to train on the material provided by a particular researcher.

- Secondly - it was supposed to use a neural network simulator as a working tool of the researcher.

- Thirdly, the assessment of the possibility of creating new, non-standard test methods using neural networks. It was supposed to check the possibility of issuing direct recommendations on the transformation of the real state of the object, bypassing the stage of setting the diagnosis (building “measured individuality” [26]).

The study was performed using neural network software simulators of the NeuroComp association [36], [41], [70], [85], [87] using psychological material collected at the Krasnoyarsk Garrison Military Hospital.

First of all, it was necessary to find out whether the level of diagnostics that has already been achieved using standard psychological tests is available to the neural networks. In order to obtain the results of maximum reliability, the psychological method LOBI [57] (Personal Questionnaire of the Bekhterevsky Institute) that was sufficiently tested by clinical practice was chosen. In addition, an important factor in choosing this particular test was the fact that the technique is clearly algorithmized and has a realization in the form of a computer test.

So, the task of the experiment was to determine how adequately a neural network simulator can reproduce the results of a typical psychological methodology in diagnosing a patient.

Having considered this problem, as well as the available neural network programs, it was decided to use the MultiNeuron neural network simulator (for a description of the package, see [85], [87]).

The MultiNeuron software package is a neurocomputer simulator implemented on the IBM PC / AT, and, among other functions, is designed to solve n-ary classification problems. This software package allows you to create and train a neural network in order to determine by the set of input signals (for example, by answering asked questions) that an object belongs to one of n (n <9) classes, which will be further numbered with integers from 1 to n. Необходимая для обучения выборка была составлена из результатов обследования по методике ЛОБИ 203 призывников и военнослужащих проходящих лечение в Красноярском гарнизонном военном госпитале и его сотрудников. При этом было получено 12 файлов задачника для MultiNeuron (по гармоническому типу выборка содержала недостаточно данных — 1 пример с наличием данного типа).

The taskbooks were formed from response lines, which are a chain of 162 signals, each of which was responsible for 1 of the LOBI questionnaire questions according to the following principle: -1 - a negative answer to this question was selected, 1 - a positive answer was selected, 0 - no question was selected. This notation was chosen based on the desirability of normalizing the input signals supplied to the input of neurons in the interval [-1,1]. The answer was set by classes, class 1 - the type is missing, class 2 - the type is diagnosed. At the same time, for the purity of the experiment according to the types of stress response itself, it was decided to abandon the diagnosis of a negative attitude towards the study and exclude such examples from the training set.

In general terms, the essence of the experiments was as follows: some examples of the original sample were randomly excluded from the learning process. After that, the neural network was trained on the remaining ones, and the selected examples made up a test sample on which it was checked how the calculated answers of the neural network correspond to the true ones.

In the process of learning neural networks with different characteristics, the author came to the conclusion that for this task it is possible to limit the number of neurons to 2 (that is, 1 neuron for each of the classes). The best results when testing on a test sample showed networks with a characteristic number of neurons c = 0.4.

For detailed processing, a sample was taken that is responsible for the ergopathic type LOBI. A series of network training experiments showed that a fully connected network trained on a sample of 152 examples does not show a better result than 90% of correct answers (on average, about 75%). The same result was confirmed during the end-to-end testing, when training was performed on 202 examples, and tested 1. After training 203 networks, a similar result was obtained by this method - 176 examples were confidently correctly identified (86.7%), uncertainly correctly - 4 (1.97% ), incorrect - 28 (13.79%), that is, the total percentage of correct answers was 88.67. It should be noted, however, that an increase in the number of examples of a training sample of up to 200 made it possible to improve the number of correct answers to a guaranteed value of 88.67% (see above). It should be assumed that a further increase in the training sample will allow us to further improve this result. In addition, the cause of errors in determining the ergopathic type by LOBI may be hiding in an insufficient number of examples with the presence of this type (the ratio of examples with the presence and absence of the type is 29: 174). This is also confirmed by the fact that among the examples with the presence of the type, the percentage of incorrect answers (12 out of 29 or 41.38%) is incomparably higher than in the sample as a whole. Thus, it can be concluded that neural networks, using certain methods of improving results (see below), allow us to create computer psychological tests that are not inferior to the currently used methods, but have a new and very important in practice property - adaptability.

2.2. Assessment of the significance of test questions

Also of interest is the result obtained when assessing the significance of input signals (respectively, LOBI questions).

Let some functional element of the neural network transform the vector of signals A arriving at it according to some law Imitation of psychological intuition using artificial neural networks where Imitation of psychological intuition using artificial neural networks - vector of adaptive parameters. Let H be the evaluation function, which depends explicitly on the output signals of the neural network and implicitly on the input signals and parameters of the neural network. In dual operation, partial derivatives will be calculated. Imitation of psychological intuition using artificial neural networks for the element v. These derivatives show the sensitivity of the estimate to the parameter change. Imitation of psychological intuition using artificial neural networks the more Imitation of psychological intuition using artificial neural networks , the more H changes when this parameter is changed for this example. It may also turn out that the derivative with respect to some parameter is very small compared to the others, which means that the parameter practically does not change during training. Thus, it is possible to single out a group of parameters, to changes of which the neural network is the least sensitive, and in the process of learning they do not change at all. Of course, to determine the group of the smallest or greatest sensitivity, it is necessary to use partial derivatives of the evaluation function by parameters in several training cycles and for all examples of the problem book. During neural network learning, the dynamics of the decrease in the evaluation function changes at different stages of learning. It can be important to determine which inputs at this stage of learning are essential for a neural network, and which are not. Such information is useful in cases where the dimension of

продолжение следует...

Продолжение:


Часть 1 Imitation of psychological intuition using artificial neural networks
Часть 2 1.7 Neural networks - Imitation of psychological intuition using artificial
Часть 3 Chapter 3. Intuitive Neural Network Prediction of Relationships - Imitation
Часть 4 LITERATURE - Imitation of psychological intuition using artificial neural networks


Comments


To leave a comment
If you have any suggestion, idea, thanks or comment, feel free to write. We really value feedback and are glad to hear your opinion.
To reply

Mathematical Methods in Psychology

Terms: Mathematical Methods in Psychology