In this paper, the concepts and tool available to use Deep learning in scholar projects are given. We carry out experiments by combining meta-classi ers with a deep arti cial neural network in four binary datasets. The results show optimal percentages of correct classi cation in some cases. The sample criteria that prevalence in this study was a representative sample over traditional criteria.
At the beginning of the 21st century, Arti cial Intelligence (AI) in its various
disciplines that integrate it, has started in a surprising way, to emulate
faithfully human behavior and reasoning. As results of this, remarkable progress have
emerged in di erent elds such as the computer-assisted medical diagnosis,
classi cation of DNA sequences, data mining, arti cial vision, voice recognition,
analysis of written language, virtual games, robotics, and any others where the
reasoning is the main element [
Among the di erent disciplines of AI, the deep learning is a novel alternative (from a few decades ago) that has as main objective to make that an intelligent agent can be capable to make its own decisions, something that currently is only possible in science ction. In this sense, di erent approaches of Arti cial Neural Networks (ANN) are used in deep learning, having as goal provides to an agent of personality comparable to a human. Among these approaches, we have Deep Neural Networks, Convolutional Neural Networks, and Deep Belief Networks.
Therefore, below is exposed brie y the topic of ANN that will be helpful to understand how deep learning works.
In this study, we described basic concepts of ANN, we mentioned some ANN tools and we experimented with various datasets.
The rest of article is divided as follow: in the section 2 the ANN, deep learning concepts are described and the tools for implement deep learning algorithms are Copsyhroigwhetd©,2019 for this paper by its authors. U mentioned, in the sections 3 and 4 the experiments and results are nally, the conclusions are described in section 5. Attribution 4.0 International (CC BY 4.0)
ANN is inspired by the way the biological nervous system works. One of the
pioneering work can be found in [
Formally, an ANN can be de ned as a processing element that receives a set
of input elements, denoted as X = x1; x2; : : : xn, which are modi ed respectively
for a series of weights W = w1; w2; : : : ; wn. The di erent values that are modi ed
by the weights are added together in what is called the net input (The net input is
the result of the addition of the products of each input value by its corresponding
weight adding a bias value or threshold of the neuron, denoted by b, which is
determined when it is activated). The activation of the neuron depends on the
activation function that acts on the net input which also regulates the output
of the neuron. As it can be observed in the gure 1, that both the sum and the
activation function represent the cell body of the neuron, in this place are realized
the corresponding mathematical calculations and the results are transmitted to
the output y [
Deep Learning is a discipline for the search of patterns through deep
abstractions that are achieved with multiple hidden layers of an ANN [
There is a wide variety of tools in which Deep learning can be implemented. Table 1 lists the ones that to the authors' knowledge are the most representative. These tools can be found in the web as open source and are oriented to any passionate person with not too much experience in programming or to self-taught persons with a little patience, in such way that they can explore the Deep learning with some tool of their choice. We carry out four experiments using datasets from public access, which are listed in Table 2.
{ Car-evaluation dataset was created from a simple hierarchical decision model,
originally developed for DEX demonstration, which is a system based on a
methodology that combines multi-attribute decision making with expert
systems [
Each dataset was used with two classes; datasets with more than two classes
were adapted to binary classes with the One-vs-All approach [
The experiments were carried out using the WEKA v.3.8 tool (Waikato
Enviroment Knowledge Analysis) [
These results are notable due to the percentage of correctly classi ed instances, which in some cases have reached the optimum value of 100%. However, it worth to mention that binary classi cation is the easiest to solve as compared with the treatment of multi-class attributes. Then, a future study will be to observe the behaviour of multi-class classi cation applying Deep Learning with these datasets.
It is important to highlight that both the cross-validation and the 2=3
1=3 sampling criteria are well established in AI for the classi cation of large
volumes of data. Therefore, being these four datasets of reasonable dimensions,
the prevalent criteria was statistical for RS, which was justi ed in reason that it
represents the equilibrium point for a given frequency or the data concentration
gave a distribution [
According to [
In these previous results can be appreciated that the binary classi cation by combining assembled algorithms with a Deep Learning algorithm give satisfactory results. Then, it can be speculated that the results in multi-class classi ca
Dataset
instances attributes classes car-evaluation Daily-days pap-smear Blood-transfusion 1728 1500 917 748 6 4 20 5 4 2 7 2 tions may be acceptable, i.e., in a range not less than 80% of correctly classi ed instances. As future work we propose: { To make experiments with the algorithm combinations of Table 3, but with multi-class datasets.
Any person, with basic knowledge of programming and computer skills, can take their rst steps and experiment in Deep Learning with the data processing tools such as those listed in Table 1; there is also a variety of public domain datasets to carry out experiments such as those presented in the previous section; In addition to the above, there is information in books, scienti c and dissemination journals, tutorials, and videos that indicate step by step how to implement a deep ANN.
Finally, as an additional comment: we would like to mention that someone can also experience with Deep Learning from a digital artistic expression perspective and make surrealist image designs such as those shown in Figure 3, because as long as AI continues on its way to make an intelligent agent able to think and feel like a human, a variety of algorithms have been developed to explore and exploit the bene ts o ered by Deep Learning, for example, generate artistic representations in digital format. A tool that allows you to create this type of art is \Deep Dream Generator", available as shareware for free on the website: https://deepdreamgenerator.com/
Authors acknowledge to the National Technological of Mexico, TECNM, and to the council of science and techonology, CONACYT, for the support given to realise this research. Authors acknowledge Editors and Reviewers for their constructive comments to produce the nal version of this manuscript.