Getapkmarkets
No Result
View All Result
  • Home
  • Business
  • Health
  • Tech
  • Home and Decor
  • Lifestyle
  • Entertainment
  • Fashion
  • Home
  • Business
  • Health
  • Tech
  • Home and Decor
  • Lifestyle
  • Entertainment
  • Fashion
No Result
View All Result
Getapkmarkets
No Result
View All Result
Home Uncategorized

Recurrent neural networks

by Joe Calvin
August 12, 2021
in Uncategorized
0
Recurrent neural networks
156
SHARES
1.9k
VIEWS
Share on FacebookShare on Twitter

In our today’s material, we will remind readers of the concept of an artificial neural network (ANN), as well as what they are, and consider the issues of solving the forecasting problem using ANNs in general and recurrent ANNs in particular.

Neural networks

First, let’s remember what an artificial neural network is. In one of the articles, I’ve seen a great explanation of one type of NN, convolutional, check it before reading further.
ANN is a network of artificial neurons (“black box” with multiple inputs and one output) that transforms a vector of input signals (data) into a vector of output signals using a function called an activation function. At the same time, at least one intermediate layer is present between the layer of “receiving” neurons and the output layer.

The type of structure of the ANN defines the concept of feedback: thus, in the ANN of direct propagation, the signal goes sequentially from the input layer of neurons along with the intermediate ones to the output; the recurrent structure implies the presence of feedbacks when the signal from the output or intermediate neurons partially arrives at the inputs of the input layer of neurons (or one of the external intermediate layers).

Recurrent neural networks

If we dwell on recurrent ANNs in a little more detail, it turns out that the most modern (and considered the most “successful”) of them originate from a structure called a multilayer perceptron (a mathematical model of the brain – ANN of direct propagation with intermediate layers). At the same time, since their inception, they have undergone significant changes – and the ANNs of the “new generation” are much simpler than their predecessors, despite the fact that they allow you to successfully solve the problems of memorizing sequences. So, for example, the most popular today Elman’s network is designed in such a way that the return signal from the inner layer goes not to the “main” input neurons, but to additional inputs – the so-called context. These neurons store information about the previous input vector (stimulus); it turns out that the output signal (network response) depends not only on the current stimulus, but also on the previous one.

See also  8 Important Reasons to Hire a Personal Injury Attorney

Solution of the forecasting problem

It is clear that Elman networks are potentially suitable for forecasting (in particular, time series). However, it is also known that feedforward neural networks successfully cope with this task – although not in all cases. As an example, we propose to consider one of the most popular variations of the forecasting problem – time series forecasting (VR). The problem statement is reduced to the choice of an arbitrary VR with N samples. Then the data is divided into three samples – training, testing, and control – and fed to the input of the ANN. The result will be presented as a time series value at the required time.

Why recurrent ANNs?

It is clear that the decision on the topology of the ANN can influence the result; But back to the beginning of the conversation: why did we deliberately choose to forecast using a recurrent network as the topic of this article? After all, if you “google”, prediction of VR in works is usually done using multilayer perceptrons (we remember that these are feedforward networks) and the backpropagation method. It is worth clarifying here: yes, indeed, in theory, such ANNs solve the forecasting problem well – provided that the degree of noise (errors and gaps in the input data), for example, of the original time series, is minimal.

In practice, the time series are quite noisy, which naturally causes problems when trying to forecast. The use of collections of feedforward networks allows to reduce the degree of error – however, this significantly increases not only the complexity of the structure itself, but also the time of its training.

See also  Paint By Numbers – Conception, Functioning, And Its Benefits

The use of Elman’s recurrent network allows solving the forecasting problem even on highly noisy time series (this is especially important for business). In the general case, this ANN is a structure of three layers, as well as a set of additional “context” elements (inputs). Feedbacks go from the hidden layer to these elements; each bond has a fixed weight of one. At each time interval, the input data is distributed among neurons in the forward direction; then shoes are applied to them the next rule. Thanks to fixed feedbacks, contextual elements always store a copy of the values from the hidden layer from the previous step (since they are sent in the opposite direction even before the training rule is applied). Thus, the noise of the time series is gradually leveled out, and along with it the error is minimized: we get a forecast that, in the general case, will be more accurate than the result of the classical approach, which is experimentally confirmed by Western works.

Conclusion

It is clear that the decision on the topology of the ANN can influence the result; But back to the beginning of the conversation: why did we deliberately choose forecasting using a recurrent network as the topic of this article? After all, if you “google”, prediction of VR in works is usually done using multilayer perceptrons (we remember that these are feedforward networks) and the backpropagation method. It is worth clarifying here: yes, indeed, in theory, such ANNs solve the forecasting problem well – provided that the degree of noise (errors and gaps in the input data), for example, of the original time series is minimal.

See also  CONTACTLESS PAYMENT SOLUTIONS: THE NEXT-GEN PAYMENT SOLUTIONS

Having considered some aspects of the practical application of neural networks to solving the forecasting problem, we can conclude that the future of forecasting belongs to the recurrent model. At least, this applies to noisy time series – and, as you know, in practice, especially in business, one cannot do without inaccuracies and gaps in data. Western science, and after it, and enthusiastic practitioners have already understood this. In the post-Soviet space, the general public has yet to reach these conclusions – we hope that this material will help our readers draw their conclusions today.

Share62Tweet39Share16

Related Posts

Gerontologist
Uncategorized

What Distinguishes a Gerontologist From a Geriatrician?

November 9, 2022
Entrepreneurs
Uncategorized

Best US Cities for Entrepreneurs in 2022

September 29, 2022
The Best Quickspin casino game
Gaming

The Trending Software That Makes for Much Improved Videos/Games and Online Entertainment

August 17, 2022
Mechanical Engineering
Uncategorized

A Career in Mechanical Engineering Abroad: Here is All You Need to Know

July 30, 2022
police
Uncategorized

Essential Skills of PSI (Police Sub Inspector)

July 27, 2022
Dating
Uncategorized

Dating apps: their essence, usefulness, and causes of unpopularity

July 27, 2022
Next Post
eCommerce SEO Experts Weigh In On the Importance of Link Building for Company Growth

eCommerce SEO Experts Weigh In On the Importance of Link Building for Company Growth

Recommended

beach accessories

7 Cool Beach Attire for Men In This Summer

July 10, 2021
3 Cheapest Online Assignment Help Services in Hong Kong

3 Cheapest Online Assignment Help Services in Hong Kong

December 2, 2021
How to Decorate a New Apartment

How to Decorate a New Apartment

September 24, 2021
What are The Common Inclusions and Exclusions of Home Insurance 

What are The Common Inclusions and Exclusions of Home Insurance 

March 2, 2020

Face Serum: A Must-Have for Maintaining a Younger Appearance

September 23, 2021
5 things to know about preeclampsia

5 things to know about preeclampsia

August 4, 2021
Getapkmarkets

© Getapkmarkets 2020 All Rights Reserved - Contact: pantheonukorg@gmail.com

Navigate Site

  • Blog
  • Disclaimer
  • Terms and Conditions
  • Privacy Policy
  • Contact Us

No Result
View All Result
  • Home
  • Business
  • Health
  • Tech
  • Home and Decor
  • Lifestyle
  • Entertainment
  • Fashion

© Getapkmarkets 2020 All Rights Reserved - Contact: pantheonukorg@gmail.com