PRE2019 3 Group10

Group Members

Name	Student Number	Study	Email
Joris Goddijn	1244648	Computer Science	j.d.goddijn@student.tue.nl
Daniël Verloop	1263544	Computer Science	a.c.verloop@student.tue.nl
Ka Yip Fung	1245300	Computer Science	k.y.fung@student.tue.nl
Rik Maas	1244503	Computer Science	r.maas@student.tue.nl
Jeroen Struijk	1252070	Computer Science	j.j.struijk@student.tue.nl

Problem Statement

Neural Networks have been used extensively in a wide variety of fields. In health care, neural networks are used for detecting certain diseases, for example tumor detection. In businesses, neural networks are used to filter job applicants: this way the business only has to take the best applicants in for interviews. In self driving cars neural networks are used to parse the visual input of the sensors of the car.
A big issue of modern neural networks is that it is a black box approach. Experts do not understand what is going on inside the neural network. This is an issue when people use neural networks to make decisions with real impactful consequences.

Our aim is to provide a tool which our users can use to have a better understanding of how the neural network they are using is making decisions. We are going to make a web application in which users can see visualizations of the inner workings of a neural network. We will focus on showing visualizations of the individual layers of a neural network. A user can select a dataset, a trained network, and a layer. And we will give them a visualization of that layer. There are many other visualization methods, for example a saliency map based on a specific input image. Or a projection of a learned dataset on 2D space to visualize how close certain classes are to each other. We will start by visualizing the layers of the network, if time allows we will also try to provide some of the other visualization methods. We will focus on neural networks used for image analysis.

Objectives

We are going to make a web application in which users can see visualizations of the inner workings of a neural network. We will focus on showing visualizations of the individual layers of a neural network. The goal of our web application is to help users understand how their neural network is making decisions.

Users and what they need

The users are people who make use of Neural Networks, like people in the health care or engineering.
Doctors analysing medical image data use them for classifying scanned images of tumors to decide whether the tumor is malicious or not.
Engineers making self driving cars can use visualizations on the networks they use as vision for their car to see what the car focuses on and what it has learned.

These users have need of an environment in which the inner workings of a neural network is visualized in such a way that these inner workings become more understandable.
It also needs to be understandable for people who do not have much pre-knowledge about neural networks or machine learning. This explanation will be a combination of some kind of model and pictures together with text that explains what is happening. Furthermore, users need to be able to explore the model freely, in such a way that they can discover different aspects of the models with various inputs.

Approach

We will use a website where we can visualize the activation of the layers in the neural network by uploading a picture/file. Based on the neural net, the website runs a forward pass on a trained network. This yields a layer activation which is returned to the user to gain information on how the neural net detect these objects.
The user will only have to select which network and dataset they want to understand. We then show visualizations and explanations. This happens on the front-end of our website. In the back-end we handle the requests and compute and create the actual visualizations which we then send back to the front-end to show the user.
We will need both front-end and back-end development.

Programming languages Front-end: Bootstrap and Vue

• Bootstrap with less. (CSS framework)
• Vue (Front-end javascript framework)
  

Back-end: Django and Keras.

• Network structures saved on the server-side. (Keras/python)
• Our own datasets on the server available to the user.
• Django (Back-end python framework)
  

Deliverables and Milestones

Week 3: Have a working website with at least 1 visualization.

• Fully functional front-end that has implemented all functionality needed for finalizing this project.
• Back-end must have a general framework for supporting several different networks/datasets.
• One visualization must be completed and fully functional to the user.

Week 7/8: Website ready for deployment, finish the project.

• Extending our visualizations with choices for several working datasets/networks.

If time allows, we want to make it possible to the user to construct his own networks for simple neural network tasks.

We want to deliver a website that is finished and user friendly. Using the site, users are able to get a better understanding of the inner workings of a convolutional neural network. This is done through visualizing the computations and transformations on the input data. Wherever necessary, we will add text to further explain the visualizations to the user.

State of the Art

Examples of existing playground where one can visualize Neural Networks:

• https://playground.tensorflow.org/
• https://convnetplayground.fastforwardlabs.com/#/models
  

The following pages explore ways to visualize Neural Networks:

• http://cs231n.github.io/understanding-cnn/
• http://yosinski.com/deepvis
• https://distill.pub/2017/feature-visualization

Task Division

For now, we have decided that Jeroen and Rik will take care of the back-end, Ka Yip and Daniël take care of the front-end and Joris will work on both (where necessary). We need a better overview of the tasks that have to be done before we can decide on a precise task division.

References

AlexNet: Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems (pp. 1097-1105).
Summary: First attempt at using CNNs for image classification for the imagenet competition. Broke the world record. Relatively small neural network used.

VGGNet: Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Summary: A later larger CNN that again broke the record on the imagenet competition. Very deep architecture with many convolutional layers and pooling layers. Power from size.

ResNet: He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
Summary: New neural network that won the imagenet competition again. The idea behind ResNet was to propagate gradients by having ‘jumps’ in the network. A start to thinking about how neural networks work and what its bottlenecks are and how to develop those aspects.

Feature space visualization: Maaten, L. V. D., & Hinton, G. (2008). Visualizing data using t-SNE. Journal of machine learning research, 9(Nov), 2579-2605.
Summary: This paper presents a method of visualizing a high feature space in 2D. This can be useful for analysing and visualising a dataset the dataset on which a neural network is training.

Saliency maps: Simonyan, K., Vedaldi, A., & Zisserman, A. (2013). Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034.
Summary: This paper explains how to create saliency maps for a given input image and CNN. It works by applying a special backward pass through the network.

Qin, Zhuwei & Yu, Fuxun & Liu, Chenchen & Chen, Xiang. (2018). How convolutional neural networks see the world - A survey of convolutional neural network visualization methods. https://arxiv.org/abs/1804.11191
Features learned by convolutional NN are hard to identify and understand for humans. This paper shows how CNN interpretability can be improves using CNN visualizations. The paper talks about several visualization methods, e.g. Activation Maximization, Network Inversion, Deconvolutional NN and Network Dissection based visualization.

Yu, Wei & Yang, Kuiyuan & Bai, Yalong & Yao, Hongxun & Rui, Yong. (2014). Visualizing and comparing Convolutional Neural Networks. https://arxiv.org/abs/1412.6631
This paper attempts to understand the internal working of a CNN, among others it uses visualization to do so.

Zeiler, Matthew D & Fergus, Rob. (2014). Visualizing and Understanding Convolutional Networks. https://link.springer.com/chapter/10.1007/978-3-319-10590-1_53
This paper introduces a visualization technique that gives insight to the function of feature layers and how classifier operates. It is said that using the visualizations, the network can be improved to outperform other networks.

Zintgraf, Luisa M. & Cohen, Taco S. & Welling, Max. (2017). A New Method to Visualize Deep Neural Networks. https://arxiv.org/abs/1603.02518
This paper presents a visualization method for the response of a NN to a specific input. It will for example highlight areas that show why (or why not) a certain class was chosen.

Zhang, Quanshi & Wu, Ying Nian & Zhu, Song-Chun. (2018). Interpretable Convolutional Neural Networks. http://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_Interpretable_Convolutional_Neural_CVPR_2018_paper.html
This paper uses a different approach to make CNN more understandable. Instead of focusing on visualization, it proposes a method to modify a traditional CNN to make it more understandable.

https://machinelearningmastery.com/how-to-visualize-filters-and-feature-maps-in-convolutional-neural-networks/
Summary: Coding tutorial on how to visualize neural networks.
Yosinski, J., Clune, J., Nguyen, A., Fuchs, T., & Lipson, H. (2015). Understanding neural networks through deep visualization. arXiv preprint arXiv:1506.06579. https://arxiv.org/abs/1506.06579
Summary: introduces several new regularization methods that combine to produce qualitatively clearer, more interpretable visualizations.
Tzeng, F. Y., & Ma, K. L. (2005). Opening the black box-data driven visualization of neural networks (pp. 383-390). IEEE. https://ieeexplore.ieee.org/abstract/document/1532820
Summary: presents designs and shows that the visualizations not only help to design more efficient neural networks, but also assists in the process of using neural networks for problem solving such as performing a classification task.
Nguyen, A., Yosinski, J., & Clune, J. (2016). Multifaceted feature visualization: Uncovering the different types of features learned by each neuron in deep neural networks. arXiv preprint arXiv:1602.03616. https://arxiv.org/abs/1602.03616
Summary: introduces an algorithm that explicitly uncovers the multiple facets of each neuron by producing a synthetic visualization of each of the types of images that activate a neuron.The paper also introduces regularization methods that produce state-of-the-art results in terms of the interpretability of images obtained by activation maximization.
Olah, C., Mordvintsev, A., & Schubert, L. (2017). Feature visualization. Distill, 2(11), e7.
https://distill.pub/2017/feature-visualization/?utm_campaign=Dynamically%20Typed&utm_medium=email&utm_source=Revue%20newsletter Summary: This article focuses on feature visualization. While feature visualization is a powerful tool, actually getting it to work involves a number of details. In this article, the writer examines the major issues and explores common approaches to solving them. The writer finds that remarkably simple methods can produce high-quality visualizations.

Leon A. Gatys, Alexander S. Ecker, Matthias Bethge (2016). Image Style Transfer Using Convolutional Neural Networks. Paper about a neural network that can seperate and combine the style and content of natural images, which provide new insights into the deep image representations learned by Convolutional Neural Networks and demonstrate their potential for high level image synthesis and manipulation.

Patrice Y. Simard, Dave Steinkraus, John C. Platt (2003) Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis. Neural networks are a powerful technology for classification of visual inputs arising from documents. However, there is a confusing plethora of different neural network methods that are used in the literature and in industry. This paper describes a set of concrete best practices that document analysis researchers can use to get good results with neural networks.

Mohammad Rastegari , Vicente Ordonez, Joseph Redmon , Ali Farhadi (2016). XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks. Paper in which two approximations of standard Convolutional Networks, using binary filters and input to convolutional layers, are proposed and compared to networks with full precision weights by running them on the ImageNet task. The approximations result in both big memory and runtime savings.

Hubert Cecotti and Axel Gräser (2011). Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces. Paper that proposes use of a Convolutional Neural Network to analyse brain activities and in this way detecting P300 brain waves.

Yunjie Liu, Evan Racah, Prabhat, Joaquin Correa, Amir Khosrowshahi, David Lavers, Kenneth Kunkel, Michael Wehner, William Collins (2016). Application of Deep Convolutional Neural Networks for Detecting Extreme Weather in Climate Datasets. In this paper, the authors developed a deep Convolutional Neural Network (CNN) classification system and demonstrated the usefulness of Deep Learning technique for tackling climate pattern detection problems.

[Rowley et al., 1998] Henry A. Rowley, Shumeer Baluja, and Takeo Kanade. Neural network based face detection.
Summary: this paper talks about convolutional neural networks that can detect faces. From this we can take how these layers are structured and how each layer can be visualized.
J.Abdul Jaleel, Sibi Salim, and Aswin.R.B. Artificial neural network based detection of skin cancer.
Summary:Here they talk about neural nets that detect skin cnacer even more reliable then humans in a early stage, something that might safe lives.
B. Lo, H.P. Chan, J.S. Lin, H Li, M.T. Freedman, and S.K. Mun. Artificial convolution neural network for medical image pattern recognition.
Summary:This is a paper that is more broad in the different deseases that it can find using CNN's.
A. Canziani & E. Culurciello, and A. Paszke. An analysis of deep neural networks for practical applications
Summary:In this paper they describe neural nets that can detect more 'normal' objects. They do this with the imagenet dataset.
L. Zhang, F. Yang, Y.D. Zhang, and Y.J. Zhu. Road crack detection using deep convolutional neural networks.
Summary:A paper that goes in detail of CNN's that detect certain road conditions like cracks that are hard to find by humans.