Reinforcement learning (RL) is a form of machine learning that can be harnessed to develop artificial intelligence by exposing the intelligence to multiple generations of data. The study demonstrates how reply buffer reward mechanics can inform the creation of new pruning methods to improve RL efficiency.

With advancements in machine learning a large data scale, high throughput virtual screening has become a more attractive method for screening drug candidates. This study compared the accuracy of molecular descriptors from two cheminformatics Mordred and PaDEL, software libraries, in characterizing the chemo-structural composition of 53 compounds from the non-nucleoside reverse transcriptase inhibitors (NNRTI) class. The classification model built with the filtered set of descriptors from Mordred was superior to the model using PaDEL descriptors. This approach can accelerate the identification of hit compounds and improve the efficiency of the drug discovery pipeline.

Based on the success of deep learning, recent works have attempted to develop a waste classification model using deep neural networks. This work presents federated learning (FL) for a solution, as it allows participants to aid in training the model using their own data. Results showed that with less clients, having a higher participation ratio resulted in less accuracy degradation by the data heterogeneity.

The authors explore how diversity in data sets contributes to bias in artificial intelligence.

Concerns regarding the rapid spread of Sars-CoV2 in early 2020 led company and local governmental officials in many states to ask people to work from home and avoid leaving their homes; measures commonly referred to as shutdowns. Here, the authors investigate how shutdowns affected carbon monoxide (CO) levels in 15 US states using publicly available data. Their results suggest that CO levels decreased as a result of these measures over the course of 2020, a trend which started to reverse after shutdowns ended.

The authors look at using publicly available data and machine learning to see if they can develop a criminal activity index for counties within the state of California.

Alzheimer’s disease (AD) is a common disease affecting 6 million people in the U.S., but no cure exists. To create therapy for AD, it is critical to detect amyloid-β protein in the brain at the early stage of AD because the accumulation of amyloid-β over 20 years is believed to cause memory impairment. However, it is difficult to examine amyloid-β in patients’ brains. In this study, we hypothesized that we could accurately predict the presence of amyloid-β using EEG data and machine learning.

Here, recognizing the difficulty associated with tracking the progression of dementia, the authors used machine learning models to predict between the presence of cognitive normalcy, mild cognitive impairment, and Alzheimer's Disease, based on blood DNA methylation levels, sex, and age. With four machine learning models and two dataset dimensionality reduction methods they achieved an accuracy of 53.33%.

Scientist are investigating the use of methane-consuming bacteria to aid the growing problem of rising greenhouse gas emissions. While previous studies claim that low-frequency electromagnetic fields can accelerate the growth rate of these bacteria, Chu et al. demonstrate that this fundamental ideology is not on the same wavelength with their data.

The authors propose a method to help first responders find the location of a person within a high-rise building in densely populated areas.