Caffe2Unity: Immersive Visualization and Interpretation of Deep Neural Networks

Deep neural networks (DNNs) dominate many tasks in the computer vision domain, but it is still difficult to understand and interpret the information contained within these networks. To gain better insight into how a network learns and operates, there is a strong need to visualize these complex structures, and this remains an important research direction. In this paper, we address the problem of how the interactive display of DNNs in a virtual reality (VR) setup can be used for general understanding and architectural assessment. We compiled a static library as a plugin for the Caffe framework in the Unity gaming engine. We used routines from this plugin to create and visualize a VR-based AlexNet architecture for an image classification task. Our layered interactive model allows the user to freely navigate back and forth within the network during visual exploration. To make the DNN model even more accessible, the user can select certain connections to understand the activity flow at a particular neuron. Our VR setup also allows users to hide the activation maps/filters or even interactively occlude certain features in an image in real-time. Furthermore, we added an interpretation module and reframed the Shapley values to give a deeper understanding of the different layers. Thus, this novel tool offers more direct access to network structures and results, and its immersive operation is especially instructive for both novices and experts in the field of DNNs.

Download Full-text

Semiotic Aggregation in Deep Learning

Entropy ◽

10.3390/e22121365 ◽

2020 ◽

Vol 22 (12) ◽

pp. 1365

Author(s):

Bogdan Muşat ◽

Răzvan Andonie

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Decision Model ◽

Deep Neural Networks ◽

Neural Model ◽

Network Layers ◽

Saliency Maps ◽

Spatial Entropy ◽

Insight Into

Convolutional neural networks utilize a hierarchy of neural network layers. The statistical aspects of information concentration in successive layers can bring an insight into the feature abstraction process. We analyze the saliency maps of these layers from the perspective of semiotics, also known as the study of signs and sign-using behavior. In computational semiotics, this aggregation operation (known as superization) is accompanied by a decrease of spatial entropy: signs are aggregated into supersign. Using spatial entropy, we compute the information content of the saliency maps and study the superization processes which take place between successive layers of the network. In our experiments, we visualize the superization process and show how the obtained knowledge can be used to explain the neural decision model. In addition, we attempt to optimize the architecture of the neural model employing a semiotic greedy technique. To the extent of our knowledge, this is the first application of computational semiotics in the analysis and interpretation of deep neural networks.

Download Full-text

Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey

Machine Learning and Knowledge Extraction ◽

10.3390/make3040048 ◽

2021 ◽

Vol 3 (4) ◽

pp. 966-989

Author(s):

Vanessa Buhrmester ◽

David Münch ◽

Michael Arens

Keyword(s):

Neural Networks ◽

Computer Vision ◽

Deep Neural Networks ◽

State Of The Art ◽

Black Box ◽

Complex Data ◽

Comprehensive Overview ◽

Nonlinear Structure ◽

Black Boxes ◽

Insight Into

Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized as being non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificially generated datasets, which often do not reflect reality. By basing decision-making algorithms on Deep Neural Networks, prejudice and unfairness may be promoted unknowingly due to a lack of transparency. Hence, several so-called explanators, or explainers, have been developed. Explainers try to give insight into the inner structure of machine learning black boxes by analyzing the connection between the input and output. In this survey, we present the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about the taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.

Download Full-text

When the state of the art is ahead of the state of understanding: Unintuitive properties of deep neural networks

Mètode Revista de difusió de la investigació ◽

10.7203/metode.9.11035 ◽

2018 ◽

Author(s):

Joan Serrà

Keyword(s):

Neural Networks ◽

Deep Learning ◽

Recent Work ◽

Deep Neural Networks ◽

State Of The Art ◽

The State ◽

Computing Power ◽

The Media ◽

Insight Into ◽

Empirical Means

Deep learning is an undeniably hot topic, not only within both academia and industry, but also among society and the media. The reasons for the advent of its popularity are manifold: unprecedented availability of data and computing power, some innovative methodologies, minor but significant technical tricks, etc. However, interestingly, the current success and practice of deep learning seems to be uncorrelated with its theoretical, more formal understanding. And with that, deep learning’s state-of-the-art presents a number of unintuitive properties or situations. In this note, I highlight some of these unintuitive properties, trying to show relevant recent work, and expose the need to get insight into them, either by formal or more empirical means.

Download Full-text

DeepFusion: Fusing User-Generated Content and Item Raw Content towards Personalized Product Recommendation

Complexity ◽

10.1155/2020/4780191 ◽

2020 ◽

Vol 2020 ◽

pp. 1-12

Author(s):

Mingxin Gan ◽

Hang Zhang

Keyword(s):

Neural Networks ◽

Deep Neural Networks ◽

Information Overload ◽

User Generated Content ◽

Latent Factors ◽

Product Recommendation ◽

Neural Architecture ◽

Multiple State ◽

Latent Representations ◽

Insight Into

Personalized recommender systems, as effective approaches for alleviating information overload, have received substantial attention in the last decade. Learning effective latent factors plays the most important role in recommendation methods. Several recent works extracted latent factors from user-generated content such as ratings and reviews and suffered from the sparsity problem and the unbalanced distribution problem. To tackle these problems, we enrich the latent representations by incorporating user-generated content and item raw content. Deep neural networks have emerged as very appealing in learning effective representations in many applications. In this paper, we propose a novel deep neural architecture named DeepFusion to jointly learn user and item representations from numerical ratings, textual reviews, and item metadata. In this framework, we utilize multiple types of deep neural networks that are best suited for each type of heterogeneous inputs and introduce an extra layer to obtain the joint representations for users and items. Experiments conducted on the Amazon product data demonstrate that our approach outperforms multiple state-of-the-art baselines. We provide further insight into the design selections and hyperparameters of our recommendation method. In addition, we further explore the relative importance of various item metadata information on improving the rating prediction performance towards personalized product recommendation, which is extremely valuable for feature extraction in practice.

Download Full-text