26 papers · ranked by Valyu relevance
Jacob Bien, Robert Tibshirani
Prototype methods seek a minimal subset of samples that can serve as a distillation or condensed view of a data set. As the size of modern data sets grows, being able to present a domain specialist with a short list of "representative" samples chosen from the data set is of increasing interpretative value. While much…
Jan Hennigs, Alison Parker, Matt Collins, Ying Jiang + 4 more
'Athanasios Kolios' 'Ewan McAdam' 'Leon Williams' 'Sean Tyrrel'] Urban sanitation in growing cities of the Global South presents particular challenges, like the speed of their growth, the high population density, and, often, the lack of existing wastewater infrastructure. This led to the Bill & Melinda Gates…
Chiyu Ma, Brandon Zhao, Chaofan Chen, Cynthia Rudin
We present ProtoConcepts, a method for interpretable image classification combining deep learning and case-based reasoning using prototypical parts. Existing work in prototype-based image classification uses a "this looks like that" reasoning process, which dissects a test image by finding prototypical parts and…
Erin Looney, Andre Buscariolli, Maria Yang, Geoffrey Raymond + 2 more
Hardware-based startups risk having longer times-to-market, deterring investment in critical fields such as cleantech, medical devices, and automation. We interviewed 55 leaders at hardware startups, mapped their development timelines, and found prototyping to be the longest development step (median of 19 weeks per…
Merel de Leeuw den Bouter, Javier Pardo, Zeno Geradts, Marcel Worring
'Marcel Worring'] In high-stakes settings, Machine Learning models that can provide predictions that are interpretable for humans are crucial. This is even more true with the advent of complex deep learning based models with a huge number of tunable parameters. Recently, prototype-based methods have emerged as a…
Authors not listed
Despite the promise of self-driving laboratories to accelerate discovery, their widespread implementation is hindered by prohibitive cost and technical complexity. We introduce BrickSDLab, a fully functional self-driving lab platform built entirely from LEGO® components, designed to bridge this accessibility gap.…
Dawid Rymarczyk, Łukasz Struski, Michał Górszczak, Koryna Lewandowska + 2 more
'Koryna Lewandowska' 'Jacek Tabor' 'Bartosz Zieliński'] Abstract. Existing prototypical-based models address the black-box nature of deep learning. However, they are sub-optimal as they often assume separate prototypes for each class, require multi-step optimization, make decisions based on prototype absence (so-called…
Yitao Peng, Lianghua He, Hongzhou Chen
—Although interpretable prototype networks have improved the transparency of deep learning image classification, the need for multiple prototypes in collaborative decision-making increases cognitive complexity and hinders user understanding. To solve this problem, this paper proposes a novel interpretable deep…
Frank Willard, Luke Moffett, Emmanuel Mokel, Jon Donnelly + 5 more
'Stark Guo' 'Julia Yang' 'Gi‐Young Kim' 'Alina Jade Barnett' 'Cynthia Rudin'] Prototypical-part models are a popular interpretable alternative to black-box deep learning models for computer vision. However, they are difficult to train, with high sensitivity to hyperparameter tuning, inhibiting their application to new…
Zhonghang Bai, Meijia Song, Xu Zhang, Jiahui Zhang
Because the judgment basis in the process of biological prototype screening is highly subjective, and because it is difficult to generate a scheme when using multiple biological prototypes for bionic design, this work proposes a biological prototype retrieval and matching method for multibiological prototype bionic…
Andong Tan, Fengtao Zhou, Hao Chen
Post-hoc explainability methods such as Grad-CAM are popular because they do not influence the performance of a trained model. However, they mainly reveal "where" a model looks at for a given input, fail to explain "what" the model looks for (e.g., what is important to classify a bird image to a Scott Oriole?).…
Heikki Sjöman, Juuso Autiosalo, Jari Juhanko, Petri Kuosmanen + 1 more
'Martin Steinert'] The subject of this study was the product development project creating a new innovative proof-of-concept (POC) prototype device that could control a connected industrial overhead crane in order to perform automatic or semi-automatic high precision lifts within a limited time frame. The development…
Wang Zhong, Zhang Yi, Jiang Yi
Inspired by a sample lesson, this paper studies and discusses children’s preferences in learning scientific concepts. In a “Dissolution” lesson, one of the students took the demonstration experiment of “carmine dissolves in Water” demonstrated by the teacher as the prototype to judge whether a new phenomenon belongs to…
Matthew R. Williams, Wayne Walter, Sliman J. Bensmaia
The loss of a hand can greatly affect quality of life. A prosthetic device that can mimic normal hand function is very important to physical and mental recuperation after hand amputation, but the currently available prosthetics do not fully meet the needs of the amputee community. Most prosthetic hands are not…
Jon Donnelly, Zhicheng Guo, Alina Jade Barnett, Hayden McTavish + 2 more
'Chaofan Chen' 'Cynthia Rudin'] Interpretability is critical for machine learning models in high-stakes settings because it allows users to verify the model's reasoning. In computer vision, prototypical part models (ProtoPNets) have become the dominant model type to meet this need. Users can easily identify flaws in…
Authors not listed
The current lithium-ion battery technology is expensive and not environmentally sustainable. While supercapacitors are an alternative they have very low energy densities making them impractical to use. Therefore, this project aimed to create an energy source that solved the problems batteries had while improving the…
Ramsés Hernández-Cerero, Juan Alejandro Flores-Campos, José Juan Mojica-Martínez, Adolfo Angel Casarez-Duran + 3 more
'José Juan Mojica-Martínez' 'Adolfo Angel Casarez-Duran' 'Luis Angel Guerrero-Hernández' 'Christopher René Torres-SanMiguel' 'Ryan Willing'] This study presents the design and experimental testing of a two-degrees-of-freedom (2DOF) elbow prosthesis prototype designed to replicate the movement patterns of a native or…
Ali Madani, Bryan McCann, Nikhil Naik, Nitish Shirish Keskar + 4 more
Generative modeling for protein engineering is key to solving fundamental problems in synthetic biology, medicine, and material science. We pose protein engineering as an unsupervised sequence generation problem in order to leverage the exponentially growing set of proteins that lack costly, structural annotations. We…
Luca Michele Martulli, Riccardo Sala, Gennaro Rollo, Milutin Kostovic + 5 more
'Milutin Kostovic' 'Marino Lavorgna' 'Andrea Sorrentino' 'Emanuele Gruppioni' 'Andrea Bernasconi' 'Ali Reza Zanjanijam'] Three-dimensional printed polymers offer unprecedented advantages for prosthetic applications, namely in terms of affordability and customisation. This work thus investigates the possibility of…
Ali Madani, Ben Krause, Eric R. Greene, Subu Subramanian + 8 more
Bypassing nature’s evolutionary trajectory, de novo protein generation—defined as creating artificial protein sequences from scratch—could enable breakthrough solutions for biomedical and environmental challenges. Viewing amino acid sequences as a language, we demonstrate that a deep learning-based language model can…
Authors not listed
Multi-material 3D printing concerns the use of two or more 3D printable materials within a single printed part. The result is a composite that benefits from the combined properties of the individual 3D printed materials. Typically, a distinct differentiation between material properties can only be achieved using…
Yaron Geffen, Yanay Ofran, Ron Unger
Recently, Deep Learning models, initially developed in the field of Natural Language Processing (NLP), were applied successfully to analyze protein sequences. A major drawback of these models is their size in terms of the number of parameters needed to be fitted and the amount of computational resources they require.…
Miguel Hernández-del-Valle, Jorge Ilarraza-Zuazo, Enrique Dios-Lázaro, Javier Rubio + 2 more
The development of novel polymer-based nanocomposites necessitates the experimental preparation and characterization of numerous compositions to identify optimal formulations. For thermoplastic-based materials, the compounding process typically involves the labor-intensive tasks of dispensing, weighing, mixing, and…
Xiaohan Lin, Zhenyu Chen, Yanheng Li, Zicheng Ma + 5 more
'Ziqiang Cao' 'Shihao Feng' 'Jun Zhang' 'Yi Qin Gao'] Modern protein engineering demands integrated sequence-structure representations to tackle key challenges in designing, modifying, and evolving proteins for specific functions. While sequence-based methods are promising for generating novel proteins, incorporating…
Liqi Kang, Banghao Wu, Bingxin Zhou, Pan Tan + 6 more
Artificial intelligence (AI) models have been used to study the compositional regularities of proteins in nature, enabling it to assist in protein design to improve the efficiency of protein engineering and reduce manufacturing cost. However, in industrial settings, proteins are often required to work in extreme…
Kaiyi Jiang, Zhaoqing Yan, Matteo Di Bernardo, Samantha R. Sgrizzi + 8 more
Directed evolution of proteins is critical for applications in basic biological research, therapeutics, diagnostics, and sustainability. However, directed evolution methods are labor intensive, cannot efficiently optimize over multiple protein properties, and are often trapped by local maxima. In silico-directed…