scholarly journals Spontaneous emergence of music detectors in a deep neural network trained for natural sound recognition

2021 ◽  
Author(s):  
Gwangsu Kim ◽  
Dong-Kyum Kim ◽  
Hawoong Jeong
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Musical Training ◽  
Temporal Structure ◽  
Population Level ◽  
Training Data ◽  
Sound Recognition ◽  
Auditory Information ◽  
Natural Sound ◽  
The Brain

Music exists in almost every society, has universal acoustic features, and is processed by distinct neural circuits in humans even with no experience of musical training. These characteristics suggest an innateness of the sense of music in our brain, but it is unclear how this innateness emerges and what functions it has. Here, using an artificial deep neural network that models the auditory information processing of the brain, we show that units tuned to music can spontaneously emerge by learning natural sound detection, even without learning music. By simulating the responses of network units to 35,487 natural sounds in 527 categories, we found that various subclasses of music are strongly clustered in the embedding space, and that this clustering arises from the music-selective response of the network units. The music-selective units encoded the temporal structure of music in multiple timescales, following the population-level response characteristics observed in the brain. The process of generalization was critical for the emergence of music-selectivity, as such properties were absent when the label of the training data was randomized to prevent generalization. We confirmed that music-selectivity can work as a functional basis for the generalization of natural sound, thereby elucidating its origin. These findings suggest that our sense of music can be innate, universally shaped by evolutionary adaptation to process natural sound.

scholarly journals Cascaded Processing of Amplitude Modulation for Natural Sound Recognition

2018 ◽  
Author(s):  
Takuya Koumura ◽  
Hiroki Terashima ◽  
Shigeto Furukawa
Keyword(s):  
Neural Network ◽  
Data Structure ◽  
Auditory System ◽  
Amplitude Modulation ◽  
Auditory Perception ◽  
Deep Neural Network ◽  
Brain Regions ◽  
Neural Representation ◽  
Sound Recognition ◽  
Natural Sound

AbstractTemporal variation of sound envelope, or amplitude modulation (AM), is essential for auditory perception of natural sounds. Neural representation of stimulus AM is successively transformed while processed by a cascade of brain regions in the auditory system. Here we sought the functional significance of such cascaded transformation of AM representation. We modelled the function of the auditory system with a deep neural network (DNN) optimized for natural sound recognition. Neurophysiological analysis of the DNN revealed that AM representation similar to the auditory system emerged during the optimization. The better-recognizing DNNs exhibited larger similarity to the auditory system. The control experiments suggest that the cascading architecture, the data structure, and the optimization objective may be essential factors for the lower, middle and higher regions, respectively. The results were consistently observed across independent datasets. These results suggest the emergence of AM representation in the auditory system during optimization for natural sound recognition.

scholarly journals Robust Approach to Supervised Deep Neural Network Training for Real-Time Object Classification in Cluttered Indoor Environment

2021 ◽  
Vol 11 (15) ◽  
pp. 7148
Author(s):  
Bedada Endale ◽  
Abera Tullu ◽  
Hayoung Shi ◽  
Beom-Soo Kang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Real Time ◽  
Network Architecture ◽  
Input Data ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Object Classification ◽  
Training Data ◽  
Gradient Descent Algorithm

Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.

scholarly journals Deep Neural Network for Predicting Ore Production by Truck-Haulage Systems in Open-Pit Mines

2020 ◽  
Vol 10 (5) ◽  
pp. 1657 ◽  
Author(s):  
Jieun Baek ◽  
Yosoon Choi
Keyword(s):  
Neural Network ◽  
Prediction Accuracy ◽  
Deep Neural Network ◽  
Training Data ◽  
Open Pit ◽  
Percentage Error ◽  
Open Pit Mines ◽  
Determination Coefficient ◽  
Packet Data ◽  
Hidden Layer

This paper proposes a deep neural network (DNN)-based method for predicting ore production by truck-haulage systems in open-pit mines. The proposed method utilizes two DNN models that are designed to predict ore production during the morning and afternoon haulage sessions, respectively. The configuration of the input nodes of the DNN models is based on truck-haulage conditions and corresponding operation times. To verify the efficacy of the proposed method, training data for the DNN models were generated by processing packet data collected over the two-month period December 2018 to January 2019. Subsequently, following training under different hidden-layer conditions, it was observed that the prediction accuracy of morning ore production was highest when the number of hidden layers and number of corresponding nodes were four and 50, respectively. The corresponding values of the determination coefficient and mean absolute percentage error (MAPE) were 0.99% and 4.78%, respectively. Further, the prediction accuracy of afternoon ore production was highest when the number of hidden layers was four and the corresponding number of nodes was 50. This yielded determination coefficient and MAPE values of 0.99% and 5.26%, respectively.

scholarly journals Deep Learning for Computational Mode Decomposition in Optical Fibers

2020 ◽  
Vol 10 (4) ◽  
pp. 1367
Author(s):  
Stefan Rothe ◽  
Qian Zhang ◽  
Nektarios Koukourakis ◽  
Jürgen W. Czarske
Keyword(s):  
Neural Network ◽  
Optical Fibers ◽  
High Performance ◽  
Deep Neural Network ◽  
Light Propagation ◽  
Training Data ◽  
Steady Increase ◽  
Cyberphysical Systems ◽  
Multimode Fibers ◽  
Propagation Of Light

Multimode fibers are regarded as the key technology for the steady increase in data rates in optical communication. However, light propagation in multimode fibers is complex and can lead to distortions in the transmission of information. Therefore, strategies to control the propagation of light should be developed. These strategies include the measurement of the amplitude and phase of the light field after propagation through the fiber. This is usually done with holographic approaches. In this paper, we discuss the use of a deep neural network to determine the amplitude and phase information from simple intensity-only camera images. A new type of training was developed, which is much more robust and precise than conventional training data designs. We show that the performance of the deep neural network is comparable to digital holography, but requires significantly smaller efforts. The fast characterization of multimode fibers is particularly suitable for high-performance applications like cyberphysical systems in the internet of things.

scholarly journals Deep Neural Network Algorithm Feedback Model with Behavioral Intelligence and Forecast Accuracy

Symmetry ◽  
2020 ◽  
Vol 12 (9) ◽  
pp. 1465
Author(s):  
Taikyeong Jeong
Keyword(s):  
Neural Network ◽  
Classification Accuracy ◽  
Deep Neural Network ◽  
Time Series Data ◽  
Training Data ◽  
Series Data ◽  
Context Aware ◽  
Data Set ◽  
Feedback Model ◽  
Data Connection

When attempting to apply a large-scale database that holds the behavioral intelligence training data of deep neural networks, the classification accuracy of the artificial intelligence algorithm needs to reflect the behavioral characteristics of the individual. When a change in behavior is recognized, that is, a feedback model based on a data connection model is applied, an analysis of time series data is performed by extracting feature vectors and interpolating data in a deep neural network to overcome the limitations of the existing statistical analysis. Using the results of the first feedback model as inputs to the deep neural network and, furthermore, as the input values of the second feedback model, and interpolating the behavioral intelligence data, that is, context awareness and lifelog data, including physical activities, involves applying the most appropriate conditions. The results of this study show that this method effectively improves the accuracy of the artificial intelligence results. In this paper, through an experiment, after extracting the feature vector of a deep neural network and restoring the missing value, the classification accuracy was verified to improve by about 20% on average. At the same time, by adding behavioral intelligence data to the time series data, a new data connection model, the Deep Neural Network Feedback Model, was proposed, and it was verified that the classification accuracy can be improved by about 8 to 9% on average. Based on the hypothesis, the F (X′) = X model was applied to thoroughly classify the training data set and test data set to present a symmetrical balance between the data connection model and the context-aware data. In addition, behavioral activity data were extrapolated in terms of context-aware and forecasting perspectives to prove the results of the experiment.

scholarly journals Deep Neural Networks for the Classification of Bank Marketing Data using Data Reduction Techniques

2019 ◽  
Vol 8 (3) ◽  
pp. 4373-4378
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Data Reduction ◽  
Deep Neural Network ◽  
Training Data ◽  
Neural Network Classifier ◽  
Data Set ◽  
Reduction Techniques ◽  
Marketing Data ◽  
Bank Marketing

The amount of data belonging to different domains are being stored rapidly in various repositories across the globe. Extracting useful information from the huge volumes of data is always difficult due to the dynamic nature of data being stored. Data Mining is a knowledge discovery process used to extract the hidden information from the data stored in various repositories, termed as warehouses in the form of patterns. One of the popular tasks of data mining is Classification, which deals with the process of distinguishing every instance of a data set into one of the predefined class labels. Banking system is one of the realworld domains, which collects huge number of client data on a daily basis. In this work, we have collected two variants of the bank marketing data set pertaining to a Portuguese financial institution consisting of 41188 and 45211 instances and performed classification on them using two data reduction techniques. Attribute subset selection has been performed on the first data set and the training data with the selected features are used in classification. Principal Component Analysis has been performed on the second data set and the training data with the extracted features are used in classification. A deep neural network classification algorithm based on Backpropagation has been developed to perform classification on both the data sets. Finally, comparisons are made on the performance of each deep neural network classifier with the four standard classifiers, namely Decision trees, Naïve Bayes, Support vector machines, and k-nearest neighbors. It has been found that the deep neural network classifier outperforms the existing classifiers in terms of accuracy

Sign in / Sign up

Export Citation Format

Share Document