Zobrazeno 1 - 10
of 3 378
pro vyhledávání: '"Aitchison P"'
Autor:
Darcie, Todd, Aitchison, J. Stewart
The responsivity of perturbation sensing can be effectively enhanced by using higher-order exceptional points (HOEPs) due to their nonlinear response to frequency perturbations. However, experimental realization can be difficult due to the stringent
Externí odkaz:
http://arxiv.org/abs/2411.18720
Autor:
Aitchison, Laurence
Here, we show that in the data-rich setting where you only train on each datapoint once (or equivalently, you only train for one epoch), standard "maximum likelihood" training optimizes the true data generating process (DGP) loss, which is equivalent
Externí odkaz:
http://arxiv.org/abs/2411.14478
Autor:
He, Zihong, Lin, Weizhe, Zheng, Hao, Zhang, Fan, Jones, Matt, Aitchison, Laurence, Xu, Xuhai, Liu, Miao, Kristensson, Per Ola, Shen, Junxiao
With the rapid advancement of AI systems, their abilities to store, retrieve, and utilize information over the long term - referred to as long-term memory - have become increasingly significant. These capabilities are crucial for enhancing the perfor
Externí odkaz:
http://arxiv.org/abs/2411.00489
Recent work developed convolutional deep kernel machines, achieving 92.7% test accuracy on CIFAR-10 using a ResNet-inspired architecture, which is SOTA for kernel methods. However, this still lags behind neural networks, which easily achieve over 94%
Externí odkaz:
http://arxiv.org/abs/2410.06171
Autor:
Aitchison, Cory T., Béri, Benjamin
Topological order is a promising basis for quantum error correction, a key milestone towards large-scale quantum computing. Floquet codes provide a dynamical scheme for this while also exhibiting Floquet-enriched topological order (FET) where anyons
Externí odkaz:
http://arxiv.org/abs/2410.02398
Sparse autoencoders (SAEs) are a promising approach to interpreting the internal representations of transformer language models. However, SAEs are usually trained separately on each transformer layer, making it difficult to use them to study how info
Externí odkaz:
http://arxiv.org/abs/2409.04185
High-resolution climate simulations are very valuable for understanding climate change impacts and planning adaptation measures. This has motivated use of regional climate models at sufficiently fine resolution to capture important small-scale atmosp
Externí odkaz:
http://arxiv.org/abs/2407.14158
Evaluating modern ML models is hard. The strong incentive for researchers and companies to report a state-of-the-art result on some metric often leads to questionable research practices (QRPs): bad practices which fall short of outright research frau
Externí odkaz:
http://arxiv.org/abs/2407.12220
In climate science, we often want to compare across different datasets. Difficulties can arise in doing this due to inevitable mismatches that arise between observational and reanalysis data, or even between different reanalyses. This misalignment ca
Externí odkaz:
http://arxiv.org/abs/2406.15027
Instruction tuning plays a crucial role in shaping the outputs of language models (LMs) to desired styles. In this work, we propose a simple yet effective method, Instruction Modelling (IM), which trains LMs by applying a loss function to the instruc
Externí odkaz:
http://arxiv.org/abs/2405.14394