Intel OpenVINO Toolkit for Computer Vision: Object Detection and Semantic Segmentation
Understanding the relation between (sensory) stimuli and the activity of neurons (i.e., "the neural code") lies at heart of understanding the computational properties of the brain. However, quantifying the information between a stimulus and a spike train has proven to be challenging. We propose a new (in vitro) method to measure how much information a single neuron transfers from the input it receives to its output spike train. The input is generated by an artificial neural network that responds to a randomly appearing and disappearing "sensory stimulus": the hidden state. The sum of this network activity is injected as current input into the neuron under investigation. The mutual information between the hidden state on the one hand and spike trains of the artificial network or the recorded spike train on the other hand can easily be estimated due to the binary shape of the hidden state. The characteristics of the input current, such as the time constant as a result of the (dis)appearance rate of the hidden state or the amplitude of the input current (the firing frequency of the neurons in the artificial network), can independently be varied. As an example, we apply this method to pyramidal neurons in the CA1 of mouse hippocampi and compare the recorded spike trains to the optimal response of the "Bayesian neuron" (BN). We conclude that like in the BN, information transfer in hippocampal pyramidal cells is non-linear and amplifying: the information loss between the artificial input and the output spike train is high if the input to the neuron (the firing of the artificial network) is not very informative about the hidden state. If the input to the neuron does contain a lot of information about the hidden state, the information loss is low. Moreover, neurons increase their firing rates in case the (dis)appearance rate is high, so that the (relative) amount of transferred information stays constant.
This article describes development experience of the neural network system for medical diagnostic of gastrointestinal diseases. There was used patient’s practical medical information for its creation. As input parameters were taken into consideration different factor groups, include demographic, patient’s complaints, life history, medical history and additional methods of research. Neural network model allowed making a significance assessment of factors, which have disease’s development influence. As a result, was designed neural network system of differential diagnosis, allowing diagnoses “gastritis”, “peptic ulcer”. In the future, developed diagnostic system can be used as a “provisional diagnosis of gastrointestinal diseases”.
The paper focuses on developing constitutive models for superplastic deformation behaviour of near-αtitanium alloy (Ti-2.5Al-1.8Mn) at elevated temperatures in a range from 840 to 890 °C and in a strain rate range from 2 × 10−4 to 8 × 10−4 s−1. Stress–strain experimental tensile tests data were used to develop the mathematical models. Both, hyperbolic sine Arrhenius-type constitutive model and artificial neural-network model were constructed. A comparative study on the competence of the developed models to predict the superplastic deformation behaviour of this alloy was made. The fitting results suggest that the artificial neural-network model has higher accuracy and is more efficient in fitting the superplastic deformation flow behaviour of near-α Titanium alloy (Ti-2.5Al-1.8Mn) at superplastic forming than the Arrhenius-type constitutive model. However, the tested results revealed that the error for the artificial neural-network is higher than the case of Arrhenius-type constitutive model for predicting the unmodelled conditions.
The article suggests the integration of a neural network as a parallel element base in a telecommunication system. In this case, the ability to learn or adapt to external conditions is applied as the main advantage. For telecommunication systems in conditions when it is possible, this ability will improve noise immunity, reliability, operability, etc. The article considers an example of the integration of a neural network into a discrete matched signal filter. It is noted that the use of parallel mathematical methods in signal processing leads to the maximum effect of increasing the quality parameters of such telecommunication elements
This article is devoted to the methodological issues of the application of artificial intelligence techniques in preventive medicine. We showed a specific example of the neural network application allows not only to diagnose cardiovascular diseases, but also on a quantitative basis to predict their emergence and development in future periods of life. This allows you to select the optimal strategy for the prevention and treatment of patients based on their individual parameters. The article concluded: recommendations for the prevention and treatment of cardiac patients should be given strictly individually, taking into account physiological peculiarities of the organism of patients. If for some patients it is useful to give up Smoking, limit the consumption of sweets, take drugs, reduce blood pressure, etc., for other patients, these recommendations may cause harm. Our intelligent system helps to identify such non-standard patients and to avoid incorrect recommendations. The prototype of the proposed system laid out in the "Projects" section on the website www.PermAi.ru.
The article deals with the features of creation of tools for monitoring and neuronet identification of complex gasair mixtures using devices such as 'electronic nose' equipped with semiconductor gas sensitive sensors in the form of matrix are considered. The results of experimental studies on the analysis and recognition of various gas mextures based on the use of artificial neural networks in the proctssing of streaming signals from a gas sensitive matrix.