no code implementations • 6 May 2024 • Lin Yang, Shawn Xu, Andrew Sellergren, Timo Kohlberger, Yuchen Zhou, Ira Ktena, Atilla Kiraly, Faruk Ahmed, Farhad Hormozdiari, Tiam Jaroensri, Eric Wang, Ellery Wulczyn, Fayaz Jamil, Theo Guidroz, Chuck Lau, Siyuan Qiao, Yun Liu, Akshay Goel, Kendall Park, Arnav Agharwal, Nick George, Yang Wang, Ryutaro Tanno, David G. T. Barrett, Wei-Hung Weng, S. Sara Mahdavi, Khaled Saab, Tao Tu, Sreenivasa Raju Kalidindi, Mozziyar Etemadi, Jorge Cuadros, Gregory Sorensen, Yossi Matias, Katherine Chou, Greg Corrado, Joelle Barral, Shravya Shetty, David Fleet, S. M. Ali Eslami, Daniel Tse, Shruthi Prabhakara, Cory McLean, Dave Steiner, Rory Pilgrim, Christopher Kelly, Shekoofeh Azizi, Daniel Golden
Building upon Gemini's multimodal models, we develop several models within the new Med-Gemini family that inherit core capabilities of Gemini and are optimized for medical use via fine-tuning with 2D and 3D radiology, histopathology, ophthalmology, dermatology and genomic data.
no code implementations • 4 Dec 2023 • Yousuf Rayhan Emon, Md Golam Rabbani, Dr. Md. Taimur Ahad, Faruk Ahmed
This comprehensive literature review is systematically based on leaf disease and machine learning methodologies applied to the detection of damaged leaves via image classification.
no code implementations • 6 Nov 2023 • Faruk Ahmed, Md. Taimur Ahad, Yousuf Rayhan Emon
This paper delivers a systematic review of the literature on machine learning methodologies applied to diagnose tea leaf disease via image classification.
no code implementations • 20 Oct 2023 • Jeremy Lai, Faruk Ahmed, Supriya Vijay, Tiam Jaroensri, Jessica Loo, Saurabh Vyawahare, Saloni Agarwal, Fayaz Jamil, Yossi Matias, Greg S. Corrado, Dale R. Webster, Jonathan Krause, Yun Liu, Po-Hsuan Cameron Chen, Ellery Wulczyn, David F. Steiner
Foundation models in histopathology that learn general representations across a wide range of tissue types, diagnoses, and magnifications offer the potential to reduce the data, compute, and technical expertise necessary to develop task-specific deep learning models with the required level of model performance.
no code implementations • ICLR 2021 • Faruk Ahmed, Yoshua Bengio, Harm van Seijen, Aaron Courville
We consider situations where the presence of dominant simpler correlations with the target variable in a training set can cause an SGD-trained neural network to be less reliant on more persistently-correlating complex features.
1 code implementation • ICLR 2021 • Samuel Lavoie, Faruk Ahmed, Aaron Courville
While unsupervised domain translation (UDT) has seen a lot of success recently, we argue that mediating its translation via categorical semantic features could broaden its applicability.
no code implementations • 27 Sep 2020 • Faruk Ahmed, Md Sultan Mahmud, Kazi Ashraf Moinuddin, Mohammed Istiaque Hyder, Mohammed Yeasin
We trained a Sidewalk Obstacle Avoidance Agent (SOAA) through reinforcement learning in a simulated robotic environment.
1 code implementation • 13 Aug 2019 • Faruk Ahmed, Aaron Courville
We critically appraise the recent interest in out-of-distribution (OOD) detection and question the practical relevance of existing benchmarks.
no code implementations • 27 Sep 2018 • Chin-wei Huang, Faruk Ahmed, Kundan Kumar, Alexandre Lacoste, Aaron Courville
Probability distillation has recently been of interest to deep learning practitioners as it presents a practical solution for sampling from autoregressive models for deployment in real-time applications.
111 code implementations • NeurIPS 2017 • Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky, Vincent Dumoulin, Aaron Courville
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability.
Ranked #3 on Image Generation on CAT 256x256
1 code implementation • 15 Nov 2016 • Ishaan Gulrajani, Kundan Kumar, Faruk Ahmed, Adrien Ali Taiga, Francesco Visin, David Vazquez, Aaron Courville
Natural image modeling is a landmark challenge of unsupervised learning.
no code implementations • ICCV 2015 • Faruk Ahmed, Dany Tarlow, Dhruv Batra
Currently, there are two dominant approaches: the first approximates the Expected-IoU (EIoU) score as Expected-Intersection-over-Expected-Union (EIoEU); and the second approach is to compute exact EIoU but only over a small set of high-quality candidate solutions.
no code implementations • 19 Nov 2015 • Michael Cogswell, Faruk Ahmed, Ross Girshick, Larry Zitnick, Dhruv Batra
One major challenge in training Deep Neural Networks is preventing overfitting.
no code implementations • 10 Dec 2014 • Faruk Ahmed, Daniel Tarlow, Dhruv Batra
The result is that we can use loss-aware prediction methodology to improve performance of the highly tuned pipeline system.