Commit f8657062 authored by burcharr's avatar burcharr 💬
Browse files

automatic writing commit ...

parent 6de33c11
...@@ -989,5 +989,76 @@ Subject\_term\_id: computational-neuroscience;computational-science;computer-sci ...@@ -989,5 +989,76 @@ Subject\_term\_id: computational-neuroscience;computational-science;computer-sci
urldate = {2021-10-26}, urldate = {2021-10-26},
date = {2002-12-01}, date = {2002-12-01},
langid = {english}, langid = {english},
keywords = {Hand segmentation, Hidden Markov models, Neural networks, Real-time gesture recognition}, keywords = {Neural networks, Hidden Markov models, Hand segmentation, Real-time gesture recognition},
}
@inproceedings{albawi_understanding_2017,
title = {Understanding of a convolutional neural network},
doi = {10.1109/ICEngTechnol.2017.8308186},
abstract = {The term Deep Learning or Deep Neural Network refers to Artificial Neural Networks ({ANN}) with multi layers. Over the last few decades, it has been considered to be one of the most powerful tools, and has become very popular in the literature as it is able to handle a huge amount of data. The interest in having deeper hidden layers has recently begun to surpass classical methods performance in different fields; especially in pattern recognition. One of the most popular deep neural networks is the Convolutional Neural Network ({CNN}). It take this name from mathematical linear operation between matrixes called convolution. {CNN} have multiple layers; including convolutional layer, non-linearity layer, pooling layer and fully-connected layer. The convolutional and fully-connected layers have parameters but pooling and non-linearity layers don't have parameters. The {CNN} has an excellent performance in machine learning problems. Specially the applications that deal with image data, such as largest image classification data set (Image Net), computer vision, and in natural language processing ({NLP}) and the results achieved were very amazing. In this paper we will explain and define all the elements and important issues related to {CNN}, and how these elements work. In addition, we will also state the parameters that effect {CNN} efficiency. This paper assumes that the readers have adequate knowledge about both machine learning and artificial neural network.},
eventtitle = {2017 International Conference on Engineering and Technology ({ICET})},
pages = {1--6},
booktitle = {2017 International Conference on Engineering and Technology ({ICET})},
author = {Albawi, Saad and Mohammed, Tareq Abed and Al-Zawi, Saad},
date = {2017-08},
keywords = {artificial neural networks, computer vision, Convolution, convolutional neural networks, Convolutional neural networks, deep learning, Feature extraction, Image edge detection, Image recognition, machine learning, Neurons},
file = {IEEE Xplore Full Text PDF:/home/robin/Zotero/storage/GI55HP88/Albawi et al. - 2017 - Understanding of a convolutional neural network.pdf:application/pdf;IEEE Xplore Abstract Record:/home/robin/Zotero/storage/JLJQ2QPK/8308186.html:text/html},
}
@article{lawrence_face_1997,
title = {Face recognition: a convolutional neural-network approach},
volume = {8},
issn = {1941-0093},
doi = {10.1109/72.554195},
shorttitle = {Face recognition},
abstract = {We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image sampling, a self-organizing map ({SOM}) neural network, and a convolutional neural network. The {SOM} provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the {SOM}, and a multilayer perceptron ({MLP}) in place of the convolutional network for comparison. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details. We analyze the computational complexity and discuss how new classes could be added to the trained recognizer.},
pages = {98--113},
number = {1},
journaltitle = {{IEEE} Transactions on Neural Networks},
author = {Lawrence, S. and Giles, C.L. and Tsoi, Ah Chung and Back, A.D.},
date = {1997-01},
note = {Conference Name: {IEEE} Transactions on Neural Networks},
keywords = {Face recognition, Feature extraction, Humans, Image databases, Image sampling, Karhunen-Loeve transforms, Multilayer perceptrons, Neural networks, Quantization, Spatial databases},
file = {IEEE Xplore Full Text PDF:/home/robin/Zotero/storage/I72QVX2C/Lawrence et al. - 1997 - Face recognition a convolutional neural-network a.pdf:application/pdf;IEEE Xplore Abstract Record:/home/robin/Zotero/storage/2ALTIFHU/554195.html:text/html},
}
@article{lecun_backpropagation_1989,
title = {Backpropagation Applied to Handwritten Zip Code Recognition},
volume = {1},
issn = {0899-7667},
doi = {10.1162/neco.1989.1.4.541},
abstract = {The ability of learning networks to generalize can be greatly enhanced by providing constraints from the task domain. This paper demonstrates how such constraints can be integrated into a backpropagation network through the architecture of the network. This approach has been successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service. A single network learns the entire recognition operation, going from the normalized image of the character to the final classification.},
pages = {541--551},
number = {4},
journaltitle = {Neural Computation},
author = {{LeCun}, Y. and Boser, B. and Denker, J. S. and Henderson, D. and Howard, R. E. and Hubbard, W. and Jackel, L. D.},
date = {1989-12},
note = {Conference Name: Neural Computation},
file = {IEEE Xplore Abstract Record:/home/robin/Zotero/storage/YRIUWZT5/6795724.html:text/html},
}
@inproceedings{le_cun_handwritten_1990,
title = {Handwritten zip code recognition with multilayer networks},
volume = {ii},
doi = {10.1109/ICPR.1990.119325},
abstract = {An application of back-propagation networks to handwritten zip code recognition is presented. Minimal preprocessing of the data is required, but the architecture of the network is highly constrained and specifically designed for the task. The input of the network consists of size-normalized images of isolated digits. The performance on zip code digits provided by the {US} Postal Service is 92\% recognition, 1\% substitution, and 7\% rejects. Structured neural networks can be viewed as statistical methods with structure which bridge the gap between purely statistical and purely structural methods.{\textless}{\textgreater}},
eventtitle = {10th International Conference on Pattern Recognition [1990] Proceedings},
pages = {35--40 vol.2},
booktitle = {10th International Conference on Pattern Recognition [1990] Proceedings},
author = {Le Cun, Y. and Matan, O. and Boser, B. and Denker, J.S. and Henderson, D. and Howard, R.E. and Hubbard, W. and Jacket, L.D. and Baird, H.S.},
date = {1990-06},
keywords = {Computer networks, Data mining, Feature extraction, Handwriting recognition, Neural networks, Nonhomogeneous media, Pattern recognition, Postal services, Spatial databases, Testing},
file = {IEEE Xplore Abstract Record:/home/robin/Zotero/storage/LEHAD9HH/119325.html:text/html;IEEE Xplore Full Text PDF:/home/robin/Zotero/storage/5NV33HI6/Le Cun et al. - 1990 - Handwritten zip code recognition with multilayer n.pdf:application/pdf},
}
@inproceedings{krizhevsky_imagenet_2012,
title = {{ImageNet} Classification with Deep Convolutional Neural Networks},
volume = {25},
url = {https://proceedings.neurips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html},
booktitle = {Advances in Neural Information Processing Systems},
publisher = {Curran Associates, Inc.},
author = {Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E},
urldate = {2021-11-03},
date = {2012},
file = {Full Text PDF:/home/robin/Zotero/storage/MRFGVD3R/Krizhevsky et al. - 2012 - ImageNet Classification with Deep Convolutional Ne.pdf:application/pdf},
} }
\ No newline at end of file
...@@ -23,8 +23,7 @@ Recently, deep neural networks have taken over the role of the state of the art ...@@ -23,8 +23,7 @@ Recently, deep neural networks have taken over the role of the state of the art
The connections' parameters are optimized using forward passes through the network of nodes, followed by the execution of the backpropagation algorithm, and an optimization step. We can accumulate all the gradients with regard to a loss function for each of the parameters and for a small subset of the data passed and perform "stochastic gradient decent" (SGD). SGD or alternative similar optimization methods like the commonly used ADAM @kingma_adam_2017 optimizer perform a parameter update step. After many such updates and if the training works well, the network parameters will have been updated to values that lead to a lower value of the loss function for the training data. However, there is no guarantee of convergence whatsoever. As mentioned above, deep neural networks can, in theory, be used to approximate arbitrary functions. Nevertheless, the parameters for the perfect approximation cannot be easily found, and empirical testing has revealed that neural networks do need a lot of training data in order to perform well, compared to classical machine learning methods. In return, with enough data, deep neural networks often outperform the classical machine learning methods. The connections' parameters are optimized using forward passes through the network of nodes, followed by the execution of the backpropagation algorithm, and an optimization step. We can accumulate all the gradients with regard to a loss function for each of the parameters and for a small subset of the data passed and perform "stochastic gradient decent" (SGD). SGD or alternative similar optimization methods like the commonly used ADAM @kingma_adam_2017 optimizer perform a parameter update step. After many such updates and if the training works well, the network parameters will have been updated to values that lead to a lower value of the loss function for the training data. However, there is no guarantee of convergence whatsoever. As mentioned above, deep neural networks can, in theory, be used to approximate arbitrary functions. Nevertheless, the parameters for the perfect approximation cannot be easily found, and empirical testing has revealed that neural networks do need a lot of training data in order to perform well, compared to classical machine learning methods. In return, with enough data, deep neural networks often outperform the classical machine learning methods.
###### Convolutional neural networks (CNNs) ###### Convolutional neural networks (CNNs)
are neural networks that are not fully connected, but work by using convolutions with a kernel, that we slide over the input. CNNs were first introduced for hand written character recognition @lecun_backpropagation_1989 @le_cun_handwritten_1990 (1989, 1990), but were later revived for computer vision tasks @krizhevsky_imagenet_2012 (2012), after more computational power was available on modern devices to train them. Since the rise of CNNs in computer vision, most computer vision problems are solved with them. The convolutions work by moving filter windows with learnable parameters (also called kernels) over the input @albawi_understanding_2017. Opposed to a fully connected network, the weights are shared over many of the nodes, because the same filters are applied over the full size of the input. CNNs have less parameters to train than a fully connected network with the same amount of nodes, which makes them easier to train. They are generally expected to perform better than FC networks, especially on image related tasks. The filters can be 2-dimensional, like for images (e.g. a 5x5 filter moved across the two axes of an image) or 1-dimensional, which can e.g. be used to slide a kernel along the time dimension of a sensor recording. Even in the 1-dimensional case, less parameters are needed compared to the application of a fully connected network. Thus, the 1-dimensional CNN is expected to be easier to train and achieve a better performance.
TODO still missing.
###### Recurrent neural networks (RNNs) ###### Recurrent neural networks (RNNs)
...@@ -117,4 +116,4 @@ D_M(\mathbf{x}) = \sqrt{(\mathbf{x}- \boldsymbol{\mu})^T\mathbf{S}^{-1}(\mathbf{ ...@@ -117,4 +116,4 @@ D_M(\mathbf{x}) = \sqrt{(\mathbf{x}- \boldsymbol{\mu})^T\mathbf{S}^{-1}(\mathbf{
\caption*{Equation \ref*{eqn:mahala}: Mahalanobis distance} \caption*{Equation \ref*{eqn:mahala}: Mahalanobis distance}
\end{figure} \end{figure}
To our knowledge, no hand washing detection method using more complicated neural networks than fully connected networks has been published as of 2021. The performance reached for the HAWAD paper could possibly be surpassed by convolutional or recurrent networks or a combination thereof, i.e. DeepConvLSTM. Added to that, the detection and separation of compulsive hand washing from ordinary hand washing has, to our knowledge, never been done before, it seems likely, that methods from hand washing detection and human activity recognition can be applied to this problem as well. To our knowledge, no hand washing detection method using more complicated neural networks than fully connected networks has been published as of 2021. The performance reached for the HAWAD paper could possibly be surpassed by convolutional or recurrent networks or a combination thereof, e.g. CNN, LSTM or DeepConvLSTM. Added to that, the detection and separation of compulsive hand washing from ordinary hand washing has, to our knowledge, never been done before. It seems likely, that methods from hand washing detection and human activity recognition can be applied to this problem as well.
\ No newline at end of file \ No newline at end of file
No preview for this file type
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment