Artificial Intelligence in Business Processes

The aim of this chapter is to establish that the principles used by neural networks can be applied to business process management. The similarity between artificial neurons and business processes, and hence between neural networks and process landscapes, will be demonstrated. This novel approach leads to an emphasis on process interactions and their effect on actions as a major governing factor in controlling process outputs. Stigmergic interaction in biological systems is explored in the context of business processes, and its potential to understand process interaction is investigated. In order to verify the use of stigmergy in business environments, a pilot study is described in which shop floor business processes in a retailing environment are observed and described using a stigmergic framework. Establishing the viability of using stigmergic interaction to control process actions and outputs is the first step towards designing neural process networks.

Dropout, a basic and effective regularization method for a deep learning model: a case study

Deep learning is based on a network of artificial neurons inspired by the human brain. This network is made up of tens or even hundreds of "layers" of neurons. The fields of application of deep learning are indeed multiple; Agriculture is one of those fields in which deep learning is used in various agricultural problems (disease detection, pest detection, and weed identification). A major problem with deep learning is how to create a model that works well, not only on the learning set but also on the validation set. Many approaches used in neural networks are explicitly designed to reduce overfit, possibly at the expense of increasing validation accuracy and training accuracy. In this paper, a basic technique (dropout) is proposed to minimize overfit, we integrated it into a convolutional neural network model to classify weed species and see how it impacts performance, a complementary solution (exponential linear units) are proposed to optimize the obtained results. The results showed that these proposed solutions are practical and highly accurate, enabling us to adopt them in deep learning models.

Synthesis of four new neuro-statistical tests for testing the hypothesis of independence of small samples of biometric data

The paper considers the analysis of small samples according to several statistical criteria to test the hypothesis of independence, since the direct calculation of the correlation coefficients using the Pearson formula gives an unacceptably high error on small biometric samples. Each of the classical statistical criteria for testing the hypothesis of independence can be replaced with an equivalent artificial neuron. Neuron training is performed based on the condition of obtaining equal probabilities of errors of the first and second kind. To improve the quality of decisions made, it is necessary to use a variety of statistical criteria, both known and new. It is necessary to form networks of artificial neurons, generalizing the number of artificial neurons that is necessary for practical use. It is shown that the classical formula for calculating the correlation coefficients can be modified with four options. This allows you to create a network of 5 artificial neurons, which is not yet able to reduce the probability of errors in comparison with the classical formula. A gain in the confidence level in the future can only be obtained when using a network of more than 23 artificial neurons, if we apply the simplest code to detect and correct errors.

Artificial Neurons Based on Ag/V2C/W Threshold Switching Memristors

Artificial synapses and neurons are two critical, fundamental bricks for constructing hardware neural networks. Owing to its high-density integration, outstanding nonlinearity, and modulated plasticity, memristors have attracted emerging attention on emulating biological synapses and neurons. However, fabricating a low-power and robust memristor-based artificial neuron without extra electrical components is still a challenge for brain-inspired systems. In this work, we demonstrate a single two-dimensional (2D) MXene(V2C)-based threshold switching (TS) memristor to emulate a leaky integrate-and-fire (LIF) neuron without auxiliary circuits, originating from the Ag diffusion-based filamentary mechanism. Moreover, our V2C-based artificial neurons faithfully achieve multiple neural functions including leaky integration, threshold-driven fire, self-relaxation, and linear strength-modulated spike frequency characteristics. This work demonstrates that three-atom-type MXene (e.g., V2C) memristors may provide an efficient method to construct the hardware neuromorphic computing systems.

Inhabiting the Uninhabitable: Encountering Atmospheres as Other Worlds

In this chapter I discuss a series of site-specific sound art works which are designed to act on our sensory system prior to our intellect. These artworks are created from my fascination with natural phenomena and systems coupled with contemporary and historical scientific ideas and discoveries. The artworks are immersive in that the participant enters into the atmosphere and ‘other worldliness’ of the work. These phenomena include the firing patterns of artificial neurons, the multiverse and the ionosphere; the meeting place between the sun and the earth. In this chapter, I draw on Juhanni Pallasmaa’s writing on sensing and perception where evoking multimodal or cross modal cues are a strategy to create atmospheres where artworks are felt rather than thought.

Emerging Artificial Neuron Devices for Probabilistic Computing

In recent decades, artificial intelligence has been successively employed in the fields of finance, commerce, and other industries. However, imitating high-level brain functions, such as imagination and inference, pose several challenges as they are relevant to a particular type of noise in a biological neuron network. Probabilistic computing algorithms based on restricted Boltzmann machine and Bayesian inference that use silicon electronics have progressed significantly in terms of mimicking probabilistic inference. However, the quasi-random noise generated from additional circuits or algorithms presents a major challenge for silicon electronics to realize the true stochasticity of biological neuron systems. Artificial neurons based on emerging devices, such as memristors and ferroelectric field-effect transistors with inherent stochasticity can produce uncertain non-linear output spikes, which may be the key to make machine learning closer to the human brain. In this article, we present a comprehensive review of the recent advances in the emerging stochastic artificial neurons (SANs) in terms of probabilistic computing. We briefly introduce the biological neurons, neuron models, and silicon neurons before presenting the detailed working mechanisms of various SANs. Finally, the merits and demerits of silicon-based and emerging neurons are discussed, and the outlook for SANs is presented.

Dissociable Neural Representations of Adversarially Perturbed Images in Convolutional Neural Networks and the Human Brain

Despite the remarkable similarities between convolutional neural networks (CNN) and the human brain, CNNs still fall behind humans in many visual tasks, indicating that there still exist considerable differences between the two systems. Here, we leverage adversarial noise (AN) and adversarial interference (AI) images to quantify the consistency between neural representations and perceptual outcomes in the two systems. Humans can successfully recognize AI images as the same categories as their corresponding regular images but perceive AN images as meaningless noise. In contrast, CNNs can recognize AN images similar as corresponding regular images but classify AI images into wrong categories with surprisingly high confidence. We use functional magnetic resonance imaging to measure brain activity evoked by regular and adversarial images in the human brain, and compare it to the activity of artificial neurons in a prototypical CNN—AlexNet. In the human brain, we find that the representational similarity between regular and adversarial images largely echoes their perceptual similarity in all early visual areas. In AlexNet, however, the neural representations of adversarial images are inconsistent with network outputs in all intermediate processing layers, providing no neural foundations for the similarities at the perceptual level. Furthermore, we show that voxel-encoding models trained on regular images can successfully generalize to the neural responses to AI images but not AN images. These remarkable differences between the human brain and AlexNet in representation-perception association suggest that future CNNs should emulate both behavior and the internal neural presentations of the human brain.