25 papers · ranked by Valyu relevance
Alexander Tscshantz, Beren Millidge, Anil K. Seth, Christopher L. Buckley + 1 more
'Christopher L. Buckley' 'Ulrik R. Beierholm'] Predictive coding is an influential model of cortical neural activity. It proposes that perceptual beliefs are furnished by sequentially minimising “prediction errors”-the differences between predicted and observed data. Implicit in this proposal is the idea that…
Joseph P. Marino, Yisong Yue, Stephan Mandt
Inference models are a key component in scaling variational inference to deep latent variable models, most notably as encoder networks in variational auto-encoders (VAEs). By replacing conventional optimization-based inference with a learned model, inference is amortized over data examples and therefore more…
Beren Millidge, Alexander Tschantz, Anil K. Seth, Christopher L. Buckley
'Christopher L. Buckley'] There are several ways to categorise reinforcement learning (RL) algorithms, such as either modelbased or model-free, policy-based or planning-based, on-policy or off-policy, and online or offline. Broad classification schemes such as these help provide a unified perspective on disparate…
Tridib K. Biswas, Jonathan Vacher, Sophie Molholm, Pascal Mamassian + 1 more
The visual system operates by segmenting visual inputs into distinct perceptual objects. Segmentation is dynamic, as revealed by the tempo of perceptual choices and neural activity in visual cortex. Dynamics for natural stimuli however, are poorly understood because natural scene segmentation is ambiguous and…
François Rousset, Raphäel Leblois, Arnaud Estoup, Jean-Michel Marin
Simulation-based methods such as approximate Bayesian computation (ABC) are widely used to infer the evolutionary history of populations from molecular genetic data. We describe and evaluate a new iterative method of statistical inference about model parameters, which revisits the idea of inferring a likelihood surface…
Priyesh Vijayan, Yash Chandak, Mitesh M. Khapra, Srinivasan Parthasarathy + 1 more
Many real-world applications deal with data that have an underlying graph structure associated with it. To perform downstream analysis on such data, it is crucial to capture relational information of nodes over their expanded neighborhood efficiently. Herein, we focus on the problem of Collective Classification (CC)…
Aolin Xu
Traditional statistical estimation, or statistical inference in general, is static, in the sense that the estimate of the quantity of interest does not change the future evolution of the quantity. In some sequential estimation problems however, we encounter the situation where the future values of the quantity to be…
Bas van Opheusden, Luigi Acerbi, Wei Ji Ma, Daniele Marinazzo
The fate of scientific hypotheses often relies on the ability of a computational model to explain the data, quantified in modern statistical approaches by the likelihood function. The log-likelihood is the key element for parameter estimation and model evaluation. However, the log-likelihood of complex models in fields…
Joseph Marino, Milan Cvitkovic, Yisong Yue
We introduce the variational filtering EM algorithm, a simple, general-purpose method for performing variational inference in dynamical latent variable models using information from only past and present variables, i.e. filtering. The algorithm is derived from the variational objective in the filtering setting and…
Shuji Shinohara, Nobuhito Manome, Kouta Suzuki, Ung-il Chung + 5 more
Bayesian inference is a process of narrowing down hypotheses (causes) to one that best explains observational data (effects). To accurately estimate a cause, a considerable amount of data is required to be observed for as long as possible. However, the object of inference is not always constant. In this case, a method…
Jinhong Shi, Fang-Xiang Wu
Background Protein inference is an important computational step in proteomics. There exists a natural nest relationship between protein inference and peptide identification, but these two steps are usually performed separately in existing methods. We believe that both peptide identification and protein inference can be…
Lippl Samuel, Peters Benjamin, Kriegeskorte Nikolaus
Recent work has suggested that feedforward residual neural networks (ResNets) approximate iterative recurrent computations. Iterative computations are useful in many domains, so they might provide good solutions for neural networks to learn. Here we quantify the degree to which ResNets learn iterative solutions and…
Matteo Priorelli, Ivilin Peev Stoianov
How can agents infer the intentions of others by simply observing their behavior? And how can they generate fast and accurate actions such as grasping a moving object on the fly? Recent advances in Bayesian model reduction have led to innovative, biologically plausible approaches to actively infer the state of affairs…
Shuji Shinohara, Nobuhito Manome, Kouta Suzuki, Ung-il Chung + 6 more
'Tatsuji Takahashi' 'Hiroshi Okamoto' 'Yukio Pegio Gunji' 'Yoshihiro Nakajima' 'Shunji Mitsuyoshi' 'Enrico Scalas'] Bayesian inference is the process of narrowing down the hypotheses (causes) to the one that best explains the observational data (effects). To accurately estimate a cause, a considerable amount of data is…
Bram Thijssen, Lodewyk F. A. Wessels, Alan D Hutson
An important feature of Bayesian statistics is the opportunity to do sequential inference: the posterior distribution obtained after seeing a dataset can be used as prior for a second inference. However, when Monte Carlo sampling methods are used for inference, we only have a set of samples from the posterior…
Yan Wang, Jiapeng Liu, Milosz Kadziński, Xiuwu Liao
We present a novel preference learning framework to capture participant preferences efficiently within limited interaction rounds. It involves three main contributions. First, we develop a variational Bayesian approach to infer the participant's preference model by estimating posterior distributions and managing…
Samuel Kessler, Adam Cobb, Tim G. J. Rudner, Stefan Zohren + 3 more
'Stephen J. Roberts' 'Irad E. Ben-Gal' 'Amichai Painsky'] Sequential Bayesian inference can be used for continual learning to prevent catastrophic forgetting of past tasks and provide an informative prior when learning new tasks. We revisit sequential Bayesian inference and assess whether using the previous task’s…
Martin Robinson, Alan Bond, Alexandr Simonov, Jie Zhang + 1 more
Recently, we have introduced the use of techniques drawn from Bayesian statistics to recover kinetic and thermodynamic parameters from voltammetric data, and were able to show that the technique of large amplitude ac voltammetry yielded significantly more accurate parameter values than the equivalent dc approach. In…
Authors not listed
Accurately modeling the dynamics of open quantum systems is critical for advancing quantum technologies, yet traditional methods often struggle with balancing accuracy and efficiency. Machine learning (ML) offers a promising alternative, particularly through recursive models that predict system evolution based on the…
Hildo Bijl
Bayesian network Authors: ['Hildo Bijl'] The field of Knowledge Tracing is focused on predicting the success rate of a student for a given skill. Modern methods like Deep Knowledge Tracing provide accurate estimates given enough data, but being based on neural networks they struggle to explain how these estimates are…
Robert Reischke
Confidence contours in parameter space are a helpful tool to compare and classify determined estimators. For more intricate parameter estimations of non-linear nature or complex error structures, the procedure of determining confidence contours is a statistically complex task. For polymer chemists, such particular…
Andreas Stuhlmüller, Robert D. Hawkins, N. Siddharth, Noah D. Goodman
'Noah D. Goodman'] Many practical techniques for probabilistic inference require a sequence of distributions that interpolate between a tractable distribution and an intractable distribution of interest. Usually, the sequences used are simple, e.g., based on geometric averages between distributions. When models are…
Chenxi Sui, Ziyang Jiang, Genesis Higueros, David Carlson + 1 more
High-performance batteries are poised for electrification of vehicles and therefore mitigate greenhouse gas emissions, which, in turn, promote a sustainable future. However, the design of optimized batteries is challenging due to the nonlinear governing physics and electrochemistry. Recent advancements have…
Authors not listed
This research presents a novel approach to obstacle detection during navigation using a combination of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. The primary objective is to generate accurate image captions that describe the content of images, which is crucial for applications such…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…