Memory, State Representations, and Recurrent Neural Networks 3. Why Sequence Models Need Memory In Part 1, sequential data was represented as an ordered collection of observations, [latex] \begin{equation} X={x_1,x_2,\ldots,x_T}. \tag{3.1}…
In this section, we establish the mathematical foundations of sequential data that will be used throughout the remainder of this article. Specifically, we discuss: What is sequential data? — Definition…
Publication details The paper is published in the Journal of Abdominal Radiology: click here Abstract Purpose Liver biopsy was considered the gold standard for diagnosing liver fibrosis; however, with advancements…
The Kolmogorov-Arnold Representation Theorem The foundation of KANs lies in the Kolmogorov-Arnold Representation Theorem (KART). This theorem states that any continuous multivariate function can be represented as a superposition of…
This post aims to give a thorough overview of the current state and future prospects of interpretability and explainability in deep learning, making it a valuable resource for students, researchers,…
In this post, I will share my GitHub repository which you may refer to develop your own model. It comprises implementation for training, testing and interpretation. This post will cover…
Biomedical image analysis The success of deep learning in image analysis has encouraged the biomedical imaging researchers to investigate its potential in analyzing various medical modalities to aid clinicians in…
What is covered? OverviewImporting librariesLoading the MNIST datasetPreprocessingLoading the trained modelEvaluationModel visualizationFilter visualizationClass activation mapLIMEConclusion Overview Unlike machine learning models, the deep learning models lack transparency in the decision making…
What is covered? OverviewDatasetImporting the librariesLoading the datasetSetting data shapeOne hot encodingBuilding and compiling the modelCallbacksTraining and visualizing the modelVisualize model output Overview This post covers the development of handwritten…
What is covered? Overfitting and underfittingRegularizationDropoutVanishing and exploding gradientWeights intialization Overfitting and underfitting During training, a neural network undergoes many epochs (may be more than 100 or 500) to learn…