1 citations · 2 across the 9 of their papers we have counts for
10 papers
Misalignment of Low-Loss Regions Causes Grokking
Yongding Tian, Zaid Al-Ars, Maksim Kitsak +1
Grokking refers to the delayed emergence of validation-set generalization after a model has already overfit the training set. Although first observed in small algorithmic tasks tra…
Connecting Independently Trained Modes via Layer-Wise Connectivity
Yongding Tian, Zaid Al-Ars, Maksim Kitsak +1
Empirical studies have shown that continuous low-loss paths can be constructed between independently trained neural network models. This phenomenon, known as mode connectivity, ref…
TINA: Acceleration of Non-NN Signal Processing Algorithms Using NN Accelerators
Christiaan Boerkamp, Steven van der Vlugt, Zaid Al-Ars
This paper introduces TINA, a novel framework for implementing non Neural Network (NN) signal processing algorithms on NN accelerators such as GPUs, TPUs or FPGAs. The key to this…
Tywaves: A Typed Waveform Viewer for Chisel
Raffaele Meloni, H. Peter Hofstee, Zaid Al-Ars
Chisel (Constructing Hardware In a Scala Embedded Language) is a broadly adopted HDL that brings object-oriented and functional programming, type-safety, and parameterization to ha…
Leveraging Apache Arrow for Zero-copy, Zero-serialization Cluster Shared Memory
Philip Groet, Joost Hoozemans, Andreas Grapentin +3
This paper describes a distributed implementation of Apache Arrow that can leverage cluster-shared load-store addressable memory that is hardware-coherent only within each node. Th…
Vanishing Variance Problem in Fully Decentralized Neural-Network Systems
Yongding Tian, Zaid Al-Ars, Maksim Kitsak +1
Federated learning and gossip learning are emerging methodologies designed to mitigate data privacy concerns by retaining training data on client devices and exclusively sharing lo…
NASH: Neural Architecture Search for Hardware-Optimized Machine Learning Models
Mengfei Ji, Yuchun Chang, Baolin Zhang +1
As machine learning (ML) algorithms get deployed in an ever-increasing number of applications, these algorithms need to achieve better trade-offs between high accuracy, high throug…
NLICE: Synthetic Medical Record Generation for Effective Primary Healthcare Differential Diagnosis
Zaid Al-Ars, Obinna Agba, Zhuoran Guo +3
This paper offers a systematic method for creating medical knowledge-grounded patient records for use in activities involving differential diagnosis. Additionally, an assessment of…
An Intermediate Representation for Composable Typed Streaming Dataflow Designs
Matthijs A. Reukers, Yongding Tian, Zaid Al-Ars +4
Tydi is an open specification for streaming dataflow designs in digital circuits, allowing designers to express how composite and variable-length data structures are transferred ov…
Tydi-lang: a language for typed streaming hardware -- A manual for future Tydi-lang compiler developers
Yongding Tian, Zaid Al-Ars, Peter Hofstee
Transferring composite data structures with variable-length fields often requires designing non-trivial protocols that are not compatible between hardware designs. When each projec…