classifiers

Following the inundation of spam calls that seem to originate from international numbers, WhatsApp’s engineering teams have moved to introduce new “classifiers” which can identify these calls and mark them as spam, sources in the know told ET.The Meta-owned instant messaging platform hopes to completely stop spam calls over the next two days, a source said, adding that the introduction of “classifiers” to identify and block these calls started working quicker than the company had hoped.“What’s new in these spam calls is…

Made by DALL-E-2 according to the author’s descriptionAs businesses increasingly employ machine learning models on collected data, one challenge that arises is the presence of positive-unlabeled (PU) datasets. These datasets contain only a small portion of labelled data, with the remaining samples being unlabeled. While unlabeled samples are typically considered negative, some of them may be positive. PU datasets are used in various business contexts, such as predicting customer churn or upsell opportunities, sales…

A hands-on tutorial explaining how to generate a custom Zero-Shot image classifier without training, using a pre-trained CLIP model. Full code included.Image generated by the author with MidjourneyImagine you need to classify whether people wear glasses, but you have no data or resources to train a custom model. In this tutorial, you will learn how to use a pre-trained CLIP model to create a custom classifier without any training required. This approach is known as Zero-Shot image classification, and it enables…

Explanation of Bias-Variance Analysis, Regularization, Performance Metrics, and an Implementation of Harmonic ClassifierFigure 1: A depiction of Results from a Bias-Variance Analysis (Source: Author)In the previous articles, we have discussed various Machine Learning methods for classification tasks. We have also used terms like Regularization, Overfitting and Underfitting repeatedly. In this article, we shall go through these terms in detail and show how you can circumvent such problems. Furthermore, we shall also…

Learn how to apply Grad-CAM using Keras and TensorFlow for explaining deep learning-based image classifiersOutput of Grad-CAM method for explaining image classifiers (image by author, base image source: Unsplash)Classical machine learning (ML) algorithms are not efficient as compared to deep learning (DL) algorithms when applied to unstructured data such as images and text. Due to the benefit of automatic feature extraction in DL as compared to manual feature engineering in classical ML, DL algorithms are more efficient…

Deep dive in the modelling assumptions and their implicationsWhile digging in the details of classical classification methods, I found sparse information about the similarities and differences of Gaussian Naive Bayes (GNB), Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA). This post centralises the information I found for the next learner.Summary: All three methods are a specific instance of The Bayes Classifier, they all deal with continuous Gaussian predictors, they differ in the assumptions…

Learn how to apply the popular explainable AI (XAI) method LIME for explaining image classifiersExplaining images using LIME (image by author)Local Interpretable Model-agnostic Explanations (LIME) is one of the most popular Explainable AI (XAI) methods used for explaining the working of machine learning and deep learning models. LIME can provide model-agnostic local explanations for solving both regression and classification problems and it can be applied with both structured datasets and even with unstructured datasets…

Photo by Isaac Smith on UnsplashLearn how to compare ML classifiers with a significance test using PythonIn my last article I talked about the importance of properly comparing different models using statistical tools, in order to choose the best model during the selection phase.In this article I want to focus on one statistical test in particular that as a data scientist or machine learning engineer you need to know. You can use this test in order to determine whether there is a statistically significant difference…

AdaSampling comes to the rescueLeaving the world of Kaggle and entering the Real World, a data scientist is frequently (read: always) faced with the problem of dirty data. Besides missing values, different units, duplicates, and whatsoever, a rather common challenge for classification tasks is the noise in data labels. And while some noise problems can be cleaned up by the analyst, others are inherently noisy or imprecise by nature.Consider the following task: predict whether a particular protein binds to a certain DNA…

Image by AuthorLearn how to compare classifiers using hypothesis testingIntroductionIn my last article I talked about the importance of properly comparing different models using statistical tools, in order to choose the best model during the selection phase.In this article I want to focus on one statistical test in particular that as a data scientist or machine learning engineer you need to know. You can use this test in order to determine whether there is a statistically significant difference between two classifiers…