scholarly journals Explaining probabilistic Artificial Intelligence (AI) models by discretizing Deep Neural Networks

2021 ◽  
Author(s):  
Rabia Saleem ◽  
Bo Yuan ◽  
Fatih Kurugollu ◽  
Ashiq Anjum
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Decision Making ◽  
Process Model ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Black Box ◽  
Decision Making Process ◽  
Deterministic Models ◽  
Know How

Artificial Intelligence (AI) models can learn from data and make decisions without any human intervention. However, the deployment of such models is challenging and risky because we do not know how the internal decision- making is happening in these models. Especially, the high-risk decisions such as medical diagnosis or automated navigation demand explainability and verification of the decision making process in AI algorithms. This research paper aims to explain Artificial Intelligence (AI) models by discretizing the black-box process model of deep neural networks using partial differential equations. The PDEs based deterministic models would minimize the time and computational cost of the decision-making process and reduce the chances of uncertainty that make the prediction more trustworthy.

scholarly journals Explaining probabilistic Artificial Intelligence (AI) models by discretizing Deep Neural Networks

2021 ◽  
Author(s):  
Rabia Saleem ◽  
Bo Yuan ◽  
Fatih Kurugollu ◽  
Ashiq Anjum
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Decision Making ◽  
Process Model ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Black Box ◽  
Decision Making Process ◽  
Deterministic Models ◽  
Know How

Artificial Intelligence (AI) models can learn from data and make decisions without any human intervention. However, the deployment of such models is challenging and risky because we do not know how the internal decision- making is happening in these models. Especially, the high-risk decisions such as medical diagnosis or automated navigation demand explainability and verification of the decision making process in AI algorithms. This research paper aims to explain Artificial Intelligence (AI) models by discretizing the black-box process model of deep neural networks using partial differential equations. The PDEs based deterministic models would minimize the time and computational cost of the decision-making process and reduce the chances of uncertainty that make the prediction more trustworthy.

scholarly journals Artificial Intelligence-Based Analytics for Diagnosis of Small Bowel Enteropathies and Black Box Feature Detection

2020 ◽  
Author(s):  
Sana Syed ◽  
Lubaina Ehsan ◽  
Aman Shrivastava ◽  
Saurav Sengupta ◽  
Marium Khan ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Decision Making ◽  
Image Analysis ◽  
Deep Learning ◽  
Small Bowel ◽  
Classification Accuracy ◽  
Black Box ◽  
Decision Making Process ◽  
Analysis Platform

Objectives: Striking histopathological overlap between distinct but related conditions poses a significant disease diagnostic challenge. There is a major clinical need to develop computational methods enabling clinicians to translate heterogeneous biomedical images into accurate and quantitative diagnostics. This need is particularly salient with small bowel enteropathies; Environmental Enteropathy (EE) and Celiac Disease (CD). We built upon our preliminary analysis by developing an artificial intelligence (AI)-based image analysis platform utilizing deep learning convolutional neural networks (CNNs) for these enteropathies. Methods: Data for secondary analysis was obtained from three primary studies at different sites. The image analysis platform for EE and CD was developed using convolutional neural networks (CNNs: ResNet and custom Shallow CNN). Gradient-weighted Class Activation Mappings (Grad-CAMs) were used to visualize the decision making process of the models. A team of medical experts simultaneously reviewed the stain color normalized images done for bias reduction and Grad-CAM visualizations to confirm structural preservation and biological relevance, respectively. Results: 461 high-resolution biopsy images from 150 children were acquired. Median age (interquartile range) was 37.5 (19.0 to 121.5) months with a roughly equal sex distribution; 77 males (51.3%). ResNet50 and Shallow CNN demonstrated 98% and 96% case-detection accuracy, respectively, which increased to 98.3% with an ensemble. Grad-CAMs demonstrated ability of the models to learn distinct microscopic morphological features. Conclusion: Our AI-based image analysis platform demonstrated high classification accuracy for small bowel enteropathies which was capable of identifying biologically relevant microscopic features, emulating human pathologist decision making process, performing in the case of suboptimal computational environment, and being modified for improving disease classification accuracy. Grad-CAMs that were employed illuminated the otherwise black box of deep learning in medicine, allowing for increased physician confidence in adopting these new technologies in clinical practice.

scholarly journals Sparsity Increases Uncertainty Estimation in Deep Ensemble

Computers ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 54
Author(s):  
Uyanga Dorjsembe ◽  
Ju Hong Lee ◽  
Bumghi Choi ◽  
Jae Won Song
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Learning ◽  
Energy Efficient ◽  
Deep Neural Networks ◽  
Black Box ◽  
Uncertainty Estimation ◽  
Point Estimation ◽  
On Demand

Deep neural networks have achieved almost human-level results in various tasks and have become popular in the broad artificial intelligence domains. Uncertainty estimation is an on-demand task caused by the black-box point estimation behavior of deep learning. The deep ensemble provides increased accuracy and estimated uncertainty; however, linearly increasing the size makes the deep ensemble unfeasible for memory-intensive tasks. To address this problem, we used model pruning and quantization with a deep ensemble and analyzed the effect in the context of uncertainty metrics. We empirically showed that the ensemble members’ disagreement increases with pruning, making models sparser by zeroing irrelevant parameters. Increased disagreement im-plies increased uncertainty, which helps in making more robust predictions. Accordingly, an energy-efficient compressed deep ensemble is appropriate for memory-intensive and uncertainty-aware tasks.

scholarly journals Machine learning in medicine: what clinicians should know

2021 ◽  
Author(s):  
JZT Sim ◽  
QW Fong ◽  
WM Huang ◽  
CH Tan
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Neural Networks ◽  
Decision Making ◽  
Deep Learning ◽  
Language Processing ◽  
Decision Making Process ◽  
Application Domain ◽  
Basic Concepts ◽  
Potential Impact

With the advent of artificial intelligence (AI), machines are increasingly being used to complete complicated tasks, yielding remarkable results. Machine learning (ML) is the most relevant subset of AI in medicine, which will soon become an integral part of our everyday practice. Therefore, physicians should acquaint themselves with ML and AI, and their role as an enabler rather than a competitor. Herein, we introduce basic concepts and terms used in AI and ML, and aim to demystify commonly used AI/ML algorithms such as learning methods including neural networks/deep learning, decision tree and application domain in computer vision and natural language processing through specific examples. We discuss how machines are already being used to augment the physician’s decision-making process, and postulate the potential impact of ML on medical practice and medical research based on its current capabilities and known limitations. Moreover, we discuss the feasibility of full machine autonomy in medicine.

scholarly journals An efficient pruning scheme of deep neural networks for Internet of Things applications

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Chen Qi ◽  
Shibo Shen ◽  
Rongpeng Li ◽  
Zhifeng Zhao ◽  
Qing Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Internet Of Things ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Superior Performance ◽  
Compact Structure ◽  
Resource Limited ◽  
Benchmark Datasets ◽  
Iot Devices

AbstractNowadays, deep neural networks (DNNs) have been rapidly deployed to realize a number of functionalities like sensing, imaging, classification, recognition, etc. However, the computational-intensive requirement of DNNs makes it difficult to be applicable for resource-limited Internet of Things (IoT) devices. In this paper, we propose a novel pruning-based paradigm that aims to reduce the computational cost of DNNs, by uncovering a more compact structure and learning the effective weights therein, on the basis of not compromising the expressive capability of DNNs. In particular, our algorithm can achieve efficient end-to-end training that transfers a redundant neural network to a compact one with a specifically targeted compression rate directly. We comprehensively evaluate our approach on various representative benchmark datasets and compared with typical advanced convolutional neural network (CNN) architectures. The experimental results verify the superior performance and robust effectiveness of our scheme. For example, when pruning VGG on CIFAR-10, our proposed scheme is able to significantly reduce its FLOPs (floating-point operations) and number of parameters with a proportion of 76.2% and 94.1%, respectively, while still maintaining a satisfactory accuracy. To sum up, our scheme could facilitate the integration of DNNs into the common machine-learning-based IoT framework and establish distributed training of neural networks in both cloud and edge.

scholarly journals Efficient Binarized Convolutional Layers for Visual Inspection Applications on Resource-Limited FPGAs and ASICs

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1511
Author(s):  
Taylor Simons ◽  
Dah-Jye Lee
Keyword(s):  
Neural Networks ◽  
Visual Inspection ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Quality Inspection ◽  
Agricultural Produce ◽  
Resource Limited ◽  
Inspection Tasks ◽  
Computational Resources ◽  
Small Models

There has been a recent surge in publications related to binarized neural networks (BNNs), which use binary values to represent both the weights and activations in deep neural networks (DNNs). Due to the bitwise nature of BNNs, there have been many efforts to implement BNNs on ASICs and FPGAs. While BNNs are excellent candidates for these kinds of resource-limited systems, most implementations still require very large FPGAs or CPU-FPGA co-processing systems. Our work focuses on reducing the computational cost of BNNs even further, making them more efficient to implement on FPGAs. We target embedded visual inspection tasks, like quality inspection sorting on manufactured parts and agricultural produce sorting. We propose a new binarized convolutional layer, called the neural jet features layer, that learns well-known classic computer vision kernels that are efficient to calculate as a group. We show that on visual inspection tasks, neural jet features perform comparably to standard BNN convolutional layers while using less computational resources. We also show that neural jet features tend to be more stable than BNN convolution layers when training small models.

scholarly journals The Application and Development of Deep Learning in Radiotherapy: A Systematic Review

2021 ◽  
Vol 20 ◽  
pp. 153303382110163
Author(s):  
Danju Huang ◽  
Han Bai ◽  
Li Wang ◽  
Yu Hou ◽  
Lan Li ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Systematic Review ◽  
Neural Networks ◽  
Decision Making ◽  
Deep Learning ◽  
Radiation Oncology ◽  
Clinical Work ◽  
Radiation Oncologists ◽  
Basic Concepts ◽  
Further Development

With the massive use of computers, the growth and explosion of data has greatly promoted the development of artificial intelligence (AI). The rise of deep learning (DL) algorithms, such as convolutional neural networks (CNN), has provided radiation oncologists with many promising tools that can simplify the complex radiotherapy process in the clinical work of radiation oncology, improve the accuracy and objectivity of diagnosis, and reduce the workload, thus enabling clinicians to spend more time on advanced decision-making tasks. As the development of DL gets closer to clinical practice, radiation oncologists will need to be more familiar with its principles to properly evaluate and use this powerful tool. In this paper, we explain the development and basic concepts of AI and discuss its application in radiation oncology based on different task categories of DL algorithms. This work clarifies the possibility of further development of DL in radiation oncology.

Sign in / Sign up

Export Citation Format

Share Document