24 papers · ranked by Valyu relevance
Christopher R. Holdgraf, Jochem W. Rieger, Cristiano Micheli, Stephanie Martin + 2 more
'Stephanie Martin' 'Robert T. Knight' 'Frederic E. Theunissen'] Cognitive neuroscience has seen rapid growth in the size and complexity of data recorded from the human brain as well as in the computational tools available to analyze this data. This data explosion has resulted in an increased use of multivariate…
Shailee Jain, Alexander G Huth
Language encoding models help explain language processing in the human brain by learning functions that predict brain responses from the language stimuli that elicited them. Current word embedding-based approaches treat each stimulus word independently and thus ignore the influence of context on language understanding.…
Paul S. Scotti, Jiageng Chen, Julie D. Golomb
Inverted encoding models (IEMs) have recently become a popular method for investigating neural representations by reconstructing the contents of perception, attention, and memory from neuroimaging data. However, the standard IEM procedure can produce spurious results and interpretation issues. Here we present a novel…
Nikolaus Kriegeskorte, Pamela K. Douglas
Encoding and decoding models are widely used in systems, cognitive, and computational neuroscience to make sense of brain-activity data. However, the interpretation of their results requires care. Decoding models can help reveal whether particular information is present in a brain region in a format the decoder can…
Erick Lamilla, Christian Sacarelo, Manuel S. Alvarez-Alvarado, Arturo Pazmino + 4 more
'Arturo Pazmino' 'Peter Iza' 'Yichuang Sun' 'Haeyoung Lee' 'Oluyomi Simpson'] Based on orbital angular momentum (OAM) properties of Laguerre-Gaussian beams LG( $p,ℓ$), a robust optical encoding model for efficient data transmission applications is designed. This paper presents an optical encoding model based on an…
Thach V. Bui
Neural coding is an important tool to discover the inner workings of mind. In this work, we propose and consider a simple but novel self-decoding model for neural coding based on the principle that the neuron body represents ongoing stimulus while dendrites are used to store that stimulus as a memory. In particular…
Guy Aridor, Francesco Grechi, Michael Woodford
We study a model of neural coding with the structure of a variational auto-encoder. The model posits that the encoding of individual stimulus values is optimally adjusted for a finite training sample of stimuli retained in memory. We demonstrate that this model can rationalize existing experimental evidence on both…
Zihan Qin, Hongrui Zhang
Large language models are turning from isolated predictors into agentic systems: they call tools, retrieve evidence, obey environment constraints, use verifiers, and complete tasks through search and multi-turn interaction. We adopts an analytical viewpoint based on "compression is intelligence": under a fixed task…
MEHRAD SARMASHGHI, SHANTANU P. JADHAV, URI T. EDEN
Neurons can code for multiple variables simultaneously and neuroscientists are often interested in classifying neurons based on their receptive field properties. Statistical models provide powerful tools for determining the factors influencing neural spiking activity and classifying individual neurons. However, as…
Peili Chen, Shiji Xiang, Linyang He, Edward F. Chang + 1 more
Recent studies have explored the correspondence between single-modality DNN models (speech or text) and specific brain networks for speech and language. The key factors underlying these correlations and their spatiotemporal evolution within the brain language network remain unclear, particularly across different DNN…
Jia Lu, Ryan Tsoi, Nan Luo, Yuanchi Ha + 8 more
Dynamical systems often generate distinct outputs according to different initial conditions, and one can infer the corresponding input configuration given an output. This property captures the essence of information encoding and decoding. Here, we demonstrate the use of self-organized patterns, combined with machine…
S. Thomas Christie, Hayden R. Johnson, Paul R. Schrater
Human response times conform to several regularities including the Hick-Hyman law, the power law of practice, speed-accuracy trade-offs, and the Stroop effect. Each of these has been thoroughly modeled in isolation, but no account describes these phenomena as predictions of a unified framework. We provide such a…
Cailum Stienstra, Liam Hebert, Patrick Thomas, Alexander Haack + 2 more
Given that Infrared (IR) spectroscopy is a crucial tool in various chemical and forensic domains, improved in silico methods for predicting experimental spectra are needed due to the time and accuracy limitations of ab initio methods. We employ Graphormer, a graph neural network (GNN) transformer, to predict IR spectra…
Yibo Yang, Stephan Mandt, Lucas Theis
Neural compression is the application of neural networks and other machine learning methods to data compression. Recent advances in statistical machine learning have opened up new possibilities for data compression, allowing compression algorithms to be learned end-to-end from data using powerful generative models such…
Authors not listed
Deep generative models are transforming early-stage drug discovery, yet most current approaches are not well suited for realistic, small-data settings and often rely on simplified molecular representations such as linear strings, overlooking the inherent graph-based structure of molecules. To address this, we first…
Haibin Wu, Xuanjun Chen, Yi‐Cheng Lin, Kai-Wei Chang + 3 more
'Alexander H. Liu' 'Hung-yi Lee'] Abstract—Neural audio codecs are initially introduced to compress audio data into compact codes to reduce transmission latency. Researchers recently discovered the potential of codecs as suitable tokenizers for converting continuous audio into discrete codes, which can be employed to…
Shengpeng Ji, Minghui Fang, Ziyue Karen Jiang, Rongjie Huang + 3 more
and Speech Language Models Authors: ['Shengpeng Ji' 'Minghui Fang' 'Ziyue Karen Jiang' 'Rongjie Huang' 'Jialung Zuo' 'Shulei Wang' 'Zhou Zhao'] In recent years, large language models have achieved significant success in generative tasks (e.g., speech cloning and audio generation) related to speech, audio, music, and…
Authors not listed
In molecular machine learning, the choice of the representation of molecules can have a significant impact on model performance. However, understanding the root causes of these performance differences often proves challenging. One promising approach to explore model behavior is representational alignment, which…
Friso H. Kingma, Pieter Abbeel, Jonathan Ho
The bits-back argument suggests that latent variable models can be turned into lossless compression schemes. Translating the bits-back argument into efficient and practical lossless compression schemes for general latent variable models, however, is still an open problem. Bits-Back with Asymmetric Numeral Systems…
Authors not listed
Compound similarity is fundamental to various cheminformatics analyses, particularly in the drug discovery industry, where the structure-activity principle is central to medicinal chemistry. Historically, binary fingerprints combined with Tanimoto and “Tanimoto-related metrics” (such as Dice, Sørensen–Dice, and…
Lei M. Li, Boris Ryabko
We consider the lossless compression bound of any individual data sequence. Conceptually, its Kolmogorov complexity is such a bound yet uncomputable. According to Shannon’s source coding theorem, the average compression bound is $nH$, where n is the number of words and H is the entropy of an oracle probability…
Angela Lopez-del Rio, Alfons Nonell-Canals, David Vidal, Alexandre Perera-Lluna
Binding prediction between targets and drug-like compounds through Deep Neural Networks have generated promising results in recent years, outperforming traditional machine learning-based methods. However, the generalization capability of these classification models is still an issue to be addressed. In this work, we…
Fuzhan Rahmanian, Robert M. Lee, Dominik Linzner, Kathrin Michel + 4 more
Predicting and monitoring battery life early and across chemistries is a significant challenge due to the plethora of degradation paths, form factors, and electrochemical testing protocols. Existing models typically translate poorly across different electrode, electrolyte, and additive materials, mostly require a fixed…
Josep Arús-Pous, Simon Viet Johansson, Oleksii Prykhodko, Esben Jannik Bjerrum + 4 more
Recurrent Neural Networks (RNNs) trained with a set of molecules represented as unique (canonical) SMILES strings, have shown the capacity to create large chemical spaces of valid and meaningful structures. Herein we perform an extensive benchmark on models trained with subsets of GDB-13 of different sizes (1 million …