Deep Learning and Neural Networks: Decision-Making Implications (original) (raw)
Related papers
Systematic Analysis of Deep Learning Models vs. Machine Learning
International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2024
Deep learning (DL) and classical machine learning (ML) models are compared and contrasted in this study, which offers a complete overview of the differences and technological improvements between the two types of models. Through an analysis of a diverse range of research publications, the study draws attention to the distinct advantages and uses of both techniques. Deep learning, which is characterized by its use of neural networks with several layers, is particularly effective at managing massive datasets that are not organized. It has also made great progress in the areas of image and audio recognition, natural language processing, and complicated pattern identification exercises. On the other hand, classic machine learning models, which are based on the extraction of features and simpler methods, continue to be quite successful in structured data situations such as classification, regression, and clustering challenges. By concentrating on aspects such as data quantity, computing resources, and unique application needs, the survey sheds light on the parameters that should be considered when selecting between deep learning and machine learning. In addition to this, it addresses the ever-changing environment of hybrid models, which combine methods from both deep learning and machine learning in order to capitalize on the advantages of both approaches. This study highlights the significance of contextual awareness in the fast-developing area of artificial intelligence by providing researchers and practitioners with useful insights that can be used to deploy the AI models that are the most appropriate for their particular requirements.
Assessing Machine Learning and Deep Learning Applications Across Diverse Domains
International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2024
Applications in machine learning (ML) and deep learning (DL) are subjected to a comprehensive analysis of their algorithmic principles, mathematical foundations, and performance indicators as part of the theoretical evaluation process. The purpose of this review is to get an understanding of the various machine learning and deep learning models, including their ability for generalization, convergence characteristics, and computational efficiency, as well as knowing their strengths and shortcomings. Through the investigation of theoretical issues such as the bias-variance tradeoff, overfitting, underfitting, and the influence of hyperparameters, researchers have the ability to enhance model designs and training techniques. As an additional benefit, the theoretical analysis offers insight on the robustness and interpretability of models, which in turn guides the development of applications that are more trustworthy and successful in a range of domains, such as computer vision, natural language processing, and predictive analytics.
Explainable Deep Learning Models for Healthcare Decision Support
International Journal of Advances in Computer Science and Technology , 2023
Deep learning has recently become a potent tool in healthcare, excelling at tasks like analyzing medical images, diagnosing diseases, and predicting patient outcomes. The Second Chapter's Literature Review explained Deep Learning in Healthcare: Current Applications and Challenges or Interpretable Techniques in Deep Learning along with Performance Evaluation of Deep Learning Models in Healthcare. It has also done Clinical Standards and Decision Support Systems. The Third Chapter Methodology discusses comprehending the subjective perceptions and interpretations of healthcare professionals regarding Explainable Deep Learning Models (EDLMs) in clinical decision-making, this study employs an interpretive research philosophy.
How do we choose the appropriate deep learning method for our case? A systematic literature review
In the era of technology 4.0, there are many problems in multiple sectors of life that are difficult for humans to solve, ranging from issues in the education quality performance system, difficulties in disease diagnosis, problems in manufacturing systems, construction, food grading, quality control, Etc. Various efforts have been made to solve these problems, from the conventional method of manually retrieving data to obtain the best solution to using a big data-based approach with deep learning. Deep learning has successfully solved problems in various sectors, proving that using big data on deep learning algorithms gives significant results. This systematic review aims to review the studies that have been carried out on applying deep learning to solve or help problems in various sectors. This systematic review shows an overview of deep learning neural networks created in the completion process, the differences in the artificial intelligent methods used, and the advantages and dis...
Explainable deep learning in healthcare: A methodological survey from an attribution view
WIREs Mechanisms of Disease
The increasing availability of large collections of electronic health record (EHR) data and unprecedented technical advances in deep learning (DL) have sparked a surge of research interest in developing DL based clinical decision support systems for diagnosis, prognosis, and treatment. Despite the recognition of the value of deep learning in healthcare, impediments to further adoption in real healthcare settings remain due to the black‐box nature of DL. Therefore, there is an emerging need for interpretable DL, which allows end users to evaluate the model decision making to know whether to accept or reject predictions and recommendations before an action is taken. In this review, we focus on the interpretability of the DL models in healthcare. We start by introducing the methods for interpretability in depth and comprehensively as a methodological reference for future researchers or clinical practitioners in this field. Besides the methods' details, we also include a discussion ...
Deep Learning of Potential Outcomes
This review systematizes the emerging literature for causal inference using deep neural networks under the potential outcomes framework. It provides an intuitive introduction on how deep learning can be used to estimate/predict heterogeneous treatment effects and extend causal inference to settings where confounding is non-linear, time varying, or encoded in text, networks, and images. To maximize accessibility, we also introduce prerequisite concepts from causal inference and deep learning. The survey differs from other treatments of deep learning and causal inference in its sharp focus on observational causal estimation, its extended exposition of key algorithms, and its detailed tutorials for implementing, training, and selecting among deep estimators in Tensorflow 2 available at github.com/kochbj/Deep-Learning-for-Causal-Inference.
Deep Learning Analysis: A Review
The Research Publication, 2018
Deep learning is a rising territory of machine learning (ML) inquires about. It includes different shrouded layers of fake neural systems. Deep learning (DL) is a part of machine learning dependent on an arrangement of calculations that endeavor to show abnormal state reflections in information. It is utilized by Google in its voice and picture acknowledgment calculations, by Netflix and Amazon to choose what you need to watch or purchase straightaway, and by specialists at MIT to anticipate what's to come. Profound Learning is utilized in different fields for accomplishing various levels of deliberation like sound, content; pictures highlight extraction and so forth. The Deep learning philosophy applies nonlinear changes and model reflections of abnormal state in extensive databases. With Deep learning capacity to make forecasts and groupings taking the upside of huge information, it can be a creative answer for issues and issues that have been never thought to be understood in such a simple way. Then again, it makes numerous difficulties on the researchers who are endeavoring to convey such another methodology. The accompanying audit sequentially shows how and in what real applications profound realizing calculations have been used. We have completed a broad writing audit and reviewed the utilization of profound learning methods on different fields.
Transportation Research Part C: Emerging Technologies, 2020
While deep neural networks (DNNs) have been increasingly applied to choice analysis showing high predictive power, it is unclear to what extent researchers can interpret economic information from DNNs. This paper demonstrates that DNNs can provide economic information as complete as classical discrete choice models (DCMs). The economic information includes choice predictions, choice probabilities, market shares, substitution patterns of alternatives, social welfare, probability derivatives, elasticities, marginal rates of substitution, and heterogeneous values of time. Unlike DCMs, DNNs can automatically learn utility functions and reveal behavioral patterns that are not prespecified by domain experts, particularly when the sample size is large. However, the economic information obtained from DNNs can be unreliable when the sample size is small, because of three challenges associated with the automatic learning capacity: high sensitivity to hyperparameters, model non-identification, and local irregularity. The first challenge is related to the statistical challenge of balancing approximation and estimation errors of DNNs, the second to the optimization challenge of identifying the global optimum in the DNN training, and the third to the robustness challenge of mitigating locally irregular patterns of estimated functions. To demonstrate the strength and challenges, we estimated the DNNs using a stated preference survey from Singapore and a revealed preference data from London, extracted the full list of economic information from the DNNs, and compared them with those from the DCMs. We found that the economic information either aggregated over trainings or population is more reliable than the disaggregate information of the individual observations or trainings, and that larger sample size, hyperparameter searching, model ensemble, and effective regularization can significantly improve the reliability of the economic information extracted from the DNNs. Future studies should investigate the requirement of sample size, better ensemble mechanisms, other regularizations and DNN architectures, better optimization algorithms, and robust DNN training methods to address DNNs' three challenges to provide more reliable economic information for DNN-based choice models.
Insight, limitations, criticism, and interpretability of the use of activation functions in deep learning artificial neural networks, 2020
ABSTRCT The existing neural networks activation functions, the Sigmoid among others is the only set uses across various applications of NNs such as microscopy, neuromorphic, optical, robotics, finance and transportation. Only one set applies to different areas of application. Also, these activation functions' selections are based on trial and error, neither emanate from the AI and or training datasets, nor from the testing data. This formed NNs' Black-box. Jamilu (2019) proposed that strong links between the AI and or training datasets and activation functions must be established. This is to replace the NNs' Black-box models with the models rely much less on experts' assumptions, and much more on input AI and or training datasets, time change and specific area of application. Thus, Jamilu (2019) proposed Criterion(s) for the rational selection of activation functions. The paper is to use superintelligent NNs for stock price predictions, portfolio optimization, and general application approaches to shed light on the paper' title.