Opening the AI Black Box: Distilling Machine-Learned Algorithms into Code by Michaud, Eric J., Liao, Isaac, Lad, Vedang, Liu, Ziming, Mudide, Anish, Loughridge, Chloe, Guo, Zifan Carl, Kheirkhah, Tara Rezaei, Vukelić, Mateja, Tegmark, Max

“…Although this mission sounds extremely challenging, we show that it is not entirely impossible by presenting a proof-of-concept method, MIPS, that can synthesize programs based on the automated mechanistic interpretability of neural networks trained to perform the desired task, auto-distilling the learned algorithm into Python code. …”
Get full text

Tree-based Data Replay for More Efficient LLM Continual Learning by Bailey, Brian

“…This study introduces an evolutionary tree-based data replay method designed to enhance the efficiency of LLMs’ continual training. …”
Get full text

Drivers’ behaviours detection with privacy protection using deep learning techniques by Xing, Tong

“…This can be done through classification from deep learning techniques with trained model by using Convolutional Neural Network (CNN). …”
Get full text

Smart hand gesture sensing with millimeter wave radar and machine learning by Sang, Jiajun

“…An innovative way of “democratic voting” of machine learning will be introduced, where the prediction results will follow the majority out of five machine learning model predictions. …”
Get full text

Challenges of online collaborative learning among special needs university students by Hidayu Shafie, Ireena Nasiha Ibnu, Noori, Abdullah, Nurhilleny Rosly, Nadia Anuar, Nur Husna Serip Mohamad

“…Therefore, the purpose of this study was to investigate challenges faced by the special needs university students when having online collaborative learning. This study was conducted quantitatively, whereby a survey method was used for the data collection. …”
Get full text

Determining bus stop locations using deep learning and time filtering by Piriyataravet, Jitpinun, Kumwilaisak, Wuttipong, Chinrungrueng, Jatuporn, Piriyatharawet, Teerawat

Get full text

Discovering and forecasting extreme events via active learning in neural operators by Pickering, Ethan, Guth, Stephen, Karniadakis, George Em, Sapsis, Themistoklis P

Get full text

Insights on Serology, CRISPR Diagnostics, and Machine Learning Architectures for Biological Sequences by Siddiqui, Sameed Muneeb

Get full text

Learning moral values through cartoons for Malaysian preschool-aged children by Abdullah, Muhammad Alif Redzuan

“…This study, which is mixed method research, aims to identify and analyse how moral values are taught in cartoons. …”
Get full text

The impact of virtual reality on programming algorithm courses on student learning outcomes by Dewi, Ika Parma, Ambiyar, Effendi, Hansi, Giatman, Muhammad, Hanafi, Hafizul Fahri, Ali, Siti Khadijah

“…The low learning outcomes of students and the limitations of learning media provide opportunities to develop innovations that can increase student engagement. …”
Get full text

Exploiting signed TV broadcasts for automatic learning of British Sign Language by Buehler, P, Everingham, M, Zisserman, A

“…The results using our method exceed the state-of-the-art for the length and stability of continuous limb tracking. …”

Tutorial on prescriptive analytics for logistics: what to predict and how to predict by Tian, Xuecheng, Yan, Ran, Wang, Shuaian, Liu, Yannick, Zhen, Lu

Get full text

Invited perspectives : how machine learning will change flood risk and impact assessment by Wagenaar, Dennis, Curran, Alex, Balbi, Mariano, Bhardwaj, Alok, Soden, Robert, Hartato, Emir, Mestav Sarica, Gizem, Ruangpan, Laddaporn, Molinario, Giuseppe, Lallemant, David

“…Machine learning methods have the potential to improve accuracy as well as reduce calculating time and model development cost. …”
Get full text

An Intelligent Cooperative Control Architecture by How, Jonathan, Choi, Han-Lim, Undurti, Aditya, Redding, Joshua

“…This paper presents an extension of existing cooperative control algorithms that have been developed for multi-UAV applications to utilize real-time observations and/or performance metric(s) in conjunction with learning methods to generate a more intelligent planner response. …”
Get full text

Using machine learning to generate novel hypotheses: increasing optimism about COVID-19 makes people less willing to justify unethical behaviors by Sheetal, Abhishek, Feng, Zhiyu, Savani, Krishna

“…The findings suggest that optimism can help reduce unethicality, and they document the utility of machine-learning methods for generating novel hypotheses.…”
Get full text

Cognitive workload quantification for air traffic controllers: an ensemble semi-supervised learning approach by Yu, Xiaoqing, Chen, Chun-Hsien, Yang, Haohan

“…To tackle this problem, this study proposes a semi-supervised learning approach to quantitatively estimate the workload of ATCOs in a continuous value. …”
Get full text

MAS.622 / 1.126J Pattern Recognition & Analysis, Fall 2000 by Massachusetts Institute of Technology. Media Laboratory.

Subjects: “…machine and human learning…”
Get full text

Lifetime estimation of DC XLPE cable insulation using BPNN-IPM improved with various schemes and optimization methods by Miftahul Fikri, Miftahul Fikri, Abdul-Malek, Zulkurnain, Mohd Esa, Mona Riza, Eko Supriyanto, Eko Supriyanto, Kartadinata, Iwa Garniwa Mulyana, Abduh, Syamsir, Christiono, Christiono

“…These results were then analyzed using two improved model schemes to accommodate the addition of variable space charge and thickness: backpropagation neural network (BPNN) and hybrid BPNN with inverse power model (BPNN-IPM). The learning process uses gradient descent (GD), genetic algorithm (GA), and Levenberg-Marquardt (LM) optimization methods. …”
Get full text

Learning to count anything: reference-less class-agnostic counting with weak supervision by Hobley, M, Prisacariu, V

Investigating graph neural networks and classical feature-extraction techniques in activity-cliff and molecular property prediction by Dablander, MF

“…It is one of the key research areas in molecular machine learning and computational drug discovery. Recently, message-passing graph neural networks (GNNs) have emerged as a novel method to learn differentiable features directly from molecular graphs. …”