From 1575fa8756b2bae23e1382ce861988007e4129d0 Mon Sep 17 00:00:00 2001 From: Andre Henriques Date: Wed, 1 Nov 2023 16:15:47 +0000 Subject: [PATCH] Work done literature review --- main.bib | 91 ++++++++++++++++++++++++++++ projectsynopsis/project-synopsis.tex | 22 ++++++- 2 files changed, 110 insertions(+), 3 deletions(-) diff --git a/main.bib b/main.bib index f80fa4a..fae5b05 100644 --- a/main.bib +++ b/main.bib @@ -11,3 +11,94 @@ year ={2023}, url ={https://aws.amazon.com/rekognition/} } +@article{lecun1989handwritten, + title={Handwritten digit recognition with a back-propagation network}, + author={LeCun, Yann and Boser, Bernhard and Denker, John and Henderson, Donnie and Howard, Richard and Hubbard, Wayne and Jackel, Lawrence}, + journal={Advances in neural information processing systems}, + volume={2}, + year={1989} +} +@article{krizhevsky2012imagenet, + title={Imagenet classification with deep convolutional neural networks}, + author={Krizhevsky, Alex and Sutskever, Ilya and Hinton, Geoffrey E}, + journal={Advances in neural information processing systems}, + volume={25}, + year={2012} +} +@article{fukushima1980neocognitron, + title={Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position}, + author={Fukushima, Kunihiko}, + journal={Biological cybernetics}, + volume={36}, + number={4}, + pages={193--202}, + year={1980}, + publisher={Springer} +} +@misc{tensorflow2015-whitepaper, +title={ {TensorFlow}: Large-Scale Machine Learning on Heterogeneous Systems}, +url={https://www.tensorflow.org/}, +note={Software available from tensorflow.org}, +author={ + Mart\'{i}n~Abadi and + Ashish~Agarwal and + Paul~Barham and + Eugene~Brevdo and + Zhifeng~Chen and + Craig~Citro and + Greg~S.~Corrado and + Andy~Davis and + Jeffrey~Dean and + Matthieu~Devin and + Sanjay~Ghemawat and + Ian~Goodfellow and + Andrew~Harp and + Geoffrey~Irving and + Michael~Isard and + Yangqing Jia and + Rafal~Jozefowicz and + Lukasz~Kaiser and + Manjunath~Kudlur and + Josh~Levenberg and + Dandelion~Man\'{e} and + Rajat~Monga and + Sherry~Moore and + Derek~Murray and + Chris~Olah and + Mike~Schuster and + Jonathon~Shlens and + Benoit~Steiner and + Ilya~Sutskever and + Kunal~Talwar and + Paul~Tucker and + Vincent~Vanhoucke and + Vijay~Vasudevan and + Fernanda~Vi\'{e}gas and + Oriol~Vinyals and + Pete~Warden and + Martin~Wattenberg and + Martin~Wicke and + Yuan~Yu and + Xiaoqiang~Zheng}, + year={2015}, +} +@misc{chollet2015keras, + title={Keras}, + author={Chollet, Fran\c{c}ois and others}, + year={2015}, + howpublished={\url{https://keras.io}}, +} +@misc{htmx, + title = {{{$<$}/{$>$} htmx - high power tools for html}}, + year = {2023}, + month = nov, + note = {[Online; accessed 1. Nov. 2023]}, + url = {https://htmx.org} +} +@misc{go, + title = {{The Go Programming Language}}, + year = {2023}, + month = nov, + note = {[Online; accessed 1. Nov. 2023]}, + url = {https://go.dev} +} diff --git a/projectsynopsis/project-synopsis.tex b/projectsynopsis/project-synopsis.tex index bece8db..297375d 100644 --- a/projectsynopsis/project-synopsis.tex +++ b/projectsynopsis/project-synopsis.tex @@ -82,24 +82,40 @@ \item Create a system to automatically to merge modules to increase efficiency \item Create a system to distribute the load of training the model's among multiple services. \end{itemize} - \section{Literature Review} + \section{Literature and Techincal Review} % 1 page of background and literature review. Here you will need to references things. Gamal et al.~\cite{gamal} introduce the concept of \ldots \subsection{Alternatives to my Project} - There currently exist systems that do image classification, like Google Vision AI, and Amazon's Rekoginition. + There currently exist systems that do image classification, like Google Vision AI\cite{google-vision-api}, and Amazon's Rekoginition\cite{amazon-rekognition}. Their tools, while providing similar services to what my project is supposed to do, it mostly focusses on general image classification rather than specific image classification, i.e. Car vs Boat, vs, Car model X vs Car model Y. \subsection{Creation Models} + The models that I will be creating will be Convolutional Neural Network(CNN)\cite{lecun1989handwritten,fukushima1980neocognitron}. + The system will be creating two types of models that cannot be expanded and models that can be expanded. For the models that can be expanded, see the section about expandable models. + The models that cannot be expanded will use a simple convolution blocks, with a similar structure as the AlexNet\cite{krizhevsky2012imagenet} ones, as the basis for the model. The size of the model will be controlled by the size of the input image, where bigger images will generate more deep and complex models. + The models will be created using TensorFlow\cite{tensorflow2015-whitepaper} and Keras\cite{chollet2015keras}. These theologies are chosen since they are both robust and used in industry. \subsection{Expandable Models} + The current most used approach for expanding a CNN model is to retrain the model. This is done by, recreating an entire new model that does the new task, using the older model as a base for the new model, or using a pretrained model as a base and training the last few layers. - \subsection{Merging models} \section{Technical overview} + \subsection{Interface} + The user will interact with the platform form via a web portal. + The web platform will be designed using HTML and a JavaScript library called HTMX\cite{htmx} for the reactivity that the pagers requires. + The web server that will act as controller will be implemented using go\cite{go}, due to its ease of use. + The web server will also interact with python to create models. Then to run the models, it will use the libraries that are available to run TensorFlow\cite{tensorflow2015-whitepaper} models for that in go. + + \subsection{Expandable Models} + The approach would be based on multiple models. The first model is a large model that will work as a feature traction model, the results of this model are then given to other smaller models. These model's purpose is to classify the results of the feature extraction model into classes. + The first model would either be an already existent pretrained model or a model that is automatically created by the platform. + The smaller models would all be all generated by the platform, this model's purpose would be actually classification. + This approach would offer a lot of expandability, as it makes the addition of a new class as easy as creating a new small model. % 1 page of overview. My approach is shown in Figure~\ref{fig:sample}. You can draw the diagram in powerpoint and save the picture \section{Workplan} % The following work plan is what I will be using for the project is shown in Figure~\ref{fig:sample2}. + Do the work! \appendix \newpage