More Like this

1. Moving forecasts forward

   https://doi.org/10.1111/nph.16838  

   DeMarche, Megan L. (September 2020, New Phytologist)

   This article is a Commentary onPatsiouet al. (2020),228: 525–540. 

   more » « less
2. The CLAS12 Forward Tagger

   https://doi.org/10.1016/j.nima.2020.163475  

   Acker, A.; Attié, D.; Aune, S.; Ball, J.; Baron, P.; Bashkanov, M.; Battaglieri, M.; Behary, R.; Benmokhtar, F.; Bersani, A.; et al (April 2020, Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment)
3. Forward build systems, formally

   https://doi.org/10.1145/3497775.3503687  

   Spall, Sarah; Mitchell, Neil; Tobin-Hochstadt, Sam (January 2022, Proceedings of the 11th ACM SIGPLAN International Conference on Certified Programs and Proofs)
4. Paths forward in radioglaciology

   https://doi.org/10.1017/aog.2023.3  

   Schroeder, Dustin M. (January 2023, Annals of Glaciology)

   Abstract Ice-penetrating radar sounding is a powerful geophysical tool for studying terrestrial and planetary ice with a rich glaciological heritage reaching back over half a century. Recent years have also seen rapid growth in both the radioglaciological community itself and in the scope and sophistication of its analysis of ice-penetrating radar data. This has been spurred by a combination of growing datasets and improvements in computational resources as well as advances in radar sounding instrumentation and platforms. Together, these developments are transforming the field and highlight exciting paths forward for future innovation and investigation. 

   more » « less
5. FFCL: Forward-Forward Net with Cortical Loops, Training and Inference on Edge Without Backpropogation

   https://doi.org/10.1145/3649476.3660391  

   Karkehabadi, Ali; Homayoun, Houman; Sasan, Avesta (June 2024, ACM)

   The Forward-Forward Learning (FFL) algorithm is a recently proposed solution for training neural networks without needing memory-intensive backpropagation. During training, labels accompany input data, classifying them as positive or negative inputs. Each layer learns its response to these inputs independently. In this study, we enhance the FFL with the following contributions: 1) We optimize label processing by segregating label and feature forwarding between layers, enhancing learning performance. 2) By revising label integration, we enhance the inference process, reduce computational complexity, and improve performance. 3) We introduce feedback loops akin to cortical loops in the brain, where information cycles through and returns to earlier neurons, enabling layers to combine complex features from previous layers with lower-level features, enhancing learning efficiency. 

   more » « less