Détail du document
Identifiant
oai:arXiv.org:2403.15360
Sujet
Computer Science - Computer Vision... Computer Science - Machine Learnin... Electrical Engineering and Systems... Electrical Engineering and Systems...Auteur
Patro, Badri N. Agneeswaran, Vijay S.Catégorie
Computer Science
Année
2024
Date de référencement
01/05/2024
Mots clés
state-of-the-art benchmarks learning mamba networks systems sequence scienceRésumé
Transformers have widely adopted attention networks for sequence mixing and MLPs for channel mixing, playing a pivotal role in achieving breakthroughs across domains.
However, recent literature highlights issues with attention networks, including low inductive bias and quadratic complexity concerning input sequence length.
State Space Models (SSMs) like S4 and others (Hippo, Global Convolutions, liquid S4, LRU, Mega, and Mamba), have emerged to address the above issues to help handle longer sequence lengths.
Mamba, while being the state-of-the-art SSM, has a stability issue when scaled to large networks for computer vision datasets.
We propose SiMBA, a new architecture that introduces Einstein FFT (EinFFT) for channel modeling by specific eigenvalue computations and uses the Mamba block for sequence modeling.
Extensive performance studies across image and time-series benchmarks demonstrate that SiMBA outperforms existing SSMs, bridging the performance gap with state-of-the-art transformers.
Notably, SiMBA establishes itself as the new state-of-the-art SSM on ImageNet and transfer learning benchmarks such as Stanford Car and Flower as well as task learning benchmarks as well as seven time series benchmark datasets.
The project page is available on this website ~\url{https://github.com/badripatro/Simba}.
Patro, Badri N.,Agneeswaran, Vijay S., 2024, SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series
Configurable Safety Tuning of Language Models with Synthetic Preference Data
data preference cst dpo configurable language safety
Affective flexibility as a developmental building block of cognitive reappraisal: An fMRI study
cognitive success affective flexibility
