This tutorial describes how to use ESP32 Machine Learning. In more detail, it covers how to use an ESP32 KNN classifier to classify objects using their colors. To implement this ESP32 Machine Learning example, we will use a color sensor (TCS3200). This project derives from the Arduino Blog where it was used a KNN classifier to recognize different fruits. In this simple ESP32 KNN Machine Learning tutorial, we will replace the Arduino Nano 33 BLE with the ESP32 and we will add a color sensor because the ESP32 doesn't have a built-in sensor.

Researchers at Shenzhen University have recently devised a method to detect images generated by deep neural networks. Their study, pre-published on arXiv, identified a set of features to capture color image statistics that can detect images generated using current artificial intelligence tools. "Our research was inspired by the rapid development of image generative models and the spread of generated fake images," Bin Li, one of the researchers who carried out the study, told Tech Xplore. "With the rise of advanced image generative models, such as generative adversarial networks (GAN) and variational autoencoders, images generated by deep networks become more and more photorealistic, and it is no longer easy to identify them with human eyes, which entails serious security risks." Recently, several researchers and global media platforms have expressed their concern with the risks posed by artificial neural networks trained to generate images. For instance, deep learning algorithms such as generative adversarial networks (GAN) and variational autoencoders could be used to generate realistic images and videos for fake news or could facilitate online frauds and the counterfeit of personal information on social media.

The multimodal web elements such as text and images are associated with inherent memory costs to store and transfer over the Internet. With the limited network connectivity in developing countries, webpage rendering gets delayed in the presence of high-memory demanding elements such as images (relative to text). To overcome this limitation, we propose a Canonical Correlation Analysis (CCA) based computational approach to replace high-cost modality with an equivalent low-cost modality. Our model learns a common subspace for low-cost and high-cost modalities that maximizes the correlation between their visual features. The obtained common subspace is used for determining the low-cost (text) element of a given high-cost (image) element for the replacement. We analyze the cost-saving performance of the proposed approach through an eye-tracking experiment conducted on real-world webpages. Our approach reduces the memory-cost by at least 83.35% by replacing images with text.

Ligand-based virtual screening is based on the assumption that similar compounds have similar biological activity [Willett, 2009]. Compound similarity can be assessed in many ways, including comparisons of molecular "fingerprints" that encode structural features or molecular properties [Todeschini and Consonni, 2009] and measurements of shape, chemical, and/or electrostatic similarity in three dimensions [Hawkins et al., 2007; Muchmore et al., 2006; Ballester and Richards, 2007]. Three-dimensional approaches such as rapid overlay of chemical structures (ROCS) [Hawkins et al., 2007] are especially interesting because of their potential to identify molecules that are similar from the point of view of a target protein but dissimilar in underlying chemical structure ("scaffold hopping"; [Böhm et al., 2004]). ROCS represents atoms as three-dimensional Gaussian functions [Grant and Pickup, 1995; Grant et al., 1996] and calculates similarity as a function of volume overlaps between alignments of pre-generated molecular conformers. Chemical ("color") similarity is measured by overlaps between dummy atoms marking interesting chemical functionalities: hydrogen bond donors and acceptors, charged functional groups, rings, and hydrophobic groups.

Given a monochrome image and some manually labeled pixels, the colorization problem is a computer-assisted process of adding color to the monochrome image. This paper proposes a novel approach to the colorization problem by formulating it as a matrix completion problem. In particular, taking a monochrome image and parts of the color pixels (labels) as inputs, we develop a robust colorization model and resort to an augmented Lagrange multiplier algorithm for solving the model. Our approach is based on the fact that a matrix can be represented as a low-rank matrix plus a sparse matrix. Our approach is effective because it is able to handle the potential noises in the monochrome image and outliers in the labels. To improve the performance of our method, we further incorporate a so-called local-color-consistency idea into our method. Empirical results on real data sets are encouraging.