Introduction to Deep Learning

Skansi, Sandro

doi:10.1007/978-3-319-73004-2

Cited by 197 publications

(102 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Deep learning is machine learning with deep artificial neural networks [ 25 ]. The essence of deep learning is the application to learning problems of artificial neural networks that contain many hidden layers.…”

Section: Introductionmentioning

confidence: 99%

SSD vs. YOLO for Detection of Outdoor Urban Advertising Panels under Multiple Variabilities

Morera

Sánchez

Moreno

et al. 2020

Sensors

View full text Add to dashboard Cite

This work compares Single Shot MultiBox Detector (SSD) and You Only Look Once (YOLO) deep neural networks for the outdoor advertisement panel detection problem by handling multiple and combined variabilities in the scenes. Publicity panel detection in images offers important advantages both in the real world as well as in the virtual one. For example, applications like Google Street View can be used for Internet publicity and when detecting these ads panels in images, it could be possible to replace the publicity appearing inside the panels by another from a funding company. In our experiments, both SSD and YOLO detectors have produced acceptable results under variable sizes of panels, illumination conditions, viewing perspectives, partial occlusion of panels, complex background and multiple panels in scenes. Due to the difficulty of finding annotated images for the considered problem, we created our own dataset for conducting the experiments. The major strength of the SSD model was the almost elimination of False Positive (FP) cases, situation that is preferable when the publicity contained inside the panel is analyzed after detecting them. On the other side, YOLO produced better panel localization results detecting a higher number of True Positive (TP) panels with a higher accuracy. Finally, a comparison of the two analyzed object detection models with different types of semantic segmentation networks and using the same evaluation metrics is also included.

show abstract

Section: Introductionmentioning

confidence: 99%

SSD vs. YOLO for Detection of Outdoor Urban Advertising Panels under Multiple Variabilities

Morera

Sánchez

Moreno

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The neural networks are organized in layers where each neuron in a layer receives the activation value of the previous layer adjusted by weight (fully connected sequential layers). This sum of multiplied weights and inputs is usually modified by an activation function e.g., sigmoid (0 to 1), Rectified Linear Unit (ReLu) (0 to inf), Tangent Hyperbolic Function (Tanh) (−1 to 1), and Softmax (0 to 1) [ 28 ]. An optimizer method is needed to update the weight values of the neurons given a cost or error function computed in the last layer (usually subtracting the desired value from the predicted value).…”

Section: Methodsmentioning

confidence: 99%

“…As an important part of machine learning techniques, the artificial neural networks (ANN) were designed in analogy to neurons and synapses. The artificial neurons (also called perceptrons) [ 27 , 28 ] send signals to others neurons through activation functions.…”

Section: Introductionmentioning

confidence: 99%

“…The learning of the network is done by calculating the error cost considering the actual and the desired output. This cost is then propagated (backpropagation) [ 27 , 28 ] in the network through optimizer function as the stochastic-gradient descent (SGD), ADAM or RMSProp [ 29 ]. Worth to mention variations of the ANNs, the Convolutional Neural Networks (CNNs) are generally used in signal and image recognition and generation, in one and two dimensions, respectively, through the use of filters or kernels (in convolutions) to seamlessly extract features from the image.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Spatial Resolution of Multispectral Rock Outcrop Images Using RGB Data and Artificial Neural Networks

Marques

Souza

Müller

et al. 2020

Sensors

View full text Add to dashboard Cite

Spectral information provided by multispectral and hyperspectral sensors has a great impact on remote sensing studies, easing the identification of carbonate outcrops that contribute to a better understanding of petroleum reservoirs. Sensors aboard satellites like Landsat series, which have data freely available usually lack the spatial resolution that suborbital sensors have. Many techniques have been developed to improve spatial resolution through data fusion. However, most of them have serious limitations regarding application and scale. Recently Super-Resolution (SR) convolution neural networks have been tested with encouraging results. However, they require large datasets, more time and computational power for training. To overcome these limitations, this work aims to increase the spatial resolution of multispectral bands from the Landsat satellite database using a modified artificial neural network that uses pixel kernels of a single spatial high-resolution RGB image from Google Earth as input. The methodology was validated with a common dataset of indoor images as well as a specific area of Landsat 8. Different downsized scale inputs were used for training where the validation used the ground truth of the original size images, obtaining comparable results to the recent works. With the method validated, we generated high spatial resolution spectral bands based on RGB images from Google Earth on a carbonated outcrop area, which were then properly classified according to the soil spectral responses making use of the advantage of a higher spatial resolution dataset.

show abstract

“…ML algorithms, among other methods, present an approach to analyzing these datasets, which are increasingly becoming available on many farms. Machine learning is a subfield of artificial intelligence [ 10 ]. According to Liu [ 11 ], ML intends to effectively reproduce human learning behavior, allowing for the automatic detection and acquisition of new information.…”

Section: Introductionmentioning

confidence: 99%

Review: Application and Prospective Discussion of Machine Learning for the Management of Dairy Farms

Cockburn

2020

Animals

View full text Add to dashboard Cite

Dairy farmers use herd management systems, behavioral sensors, feeding lists, breeding schedules, and health records to document herd characteristics. Consequently, large amounts of dairy data are becoming available. However, a lack of data integration makes it difficult for farmers to analyze the data on their dairy farm, which indicates that these data are currently not being used to their full potential. Hence, multiple issues in dairy farming such as low longevity, poor performance, and health issues remain. We aimed to evaluate whether machine learning (ML) methods can solve some of these existing issues in dairy farming. This review summarizes peer-reviewed ML papers published in the dairy sector between 2015 and 2020. Ultimately, 97 papers from the subdomains of management, physiology, reproduction, behavior analysis, and feeding were considered in this review. The results confirm that ML algorithms have become common tools in most areas of dairy research, particularly to predict data. Despite the quantity of research available, most tested algorithms have not performed sufficiently for a reliable implementation in practice. This may be due to poor training data. The availability of data resources from multiple farms covering longer periods would be useful to improve prediction accuracies. In conclusion, ML is a promising tool in dairy research, which could be used to develop and improve decision support for farmers. As the cow is a multifactorial system, ML algorithms could analyze integrated data sources that describe and ultimately allow managing cows according to all relevant influencing factors. However, both the integration of multiple data sources and the obtainability of public data currently remain challenging.

show abstract

Introduction to Deep Learning

Cited by 197 publications

References 1 publication

SSD vs. YOLO for Detection of Outdoor Urban Advertising Panels under Multiple Variabilities

SSD vs. YOLO for Detection of Outdoor Urban Advertising Panels under Multiple Variabilities

Improving Spatial Resolution of Multispectral Rock Outcrop Images Using RGB Data and Artificial Neural Networks

Review: Application and Prospective Discussion of Machine Learning for the Management of Dairy Farms

Contact Info

Product

Resources

About