Robert Ravier
YOU?
Author Swipe
View article: Consistent coordination patterns provide near perfect behavior decoding in a comprehensive motor program for insect flight
Consistent coordination patterns provide near perfect behavior decoding in a comprehensive motor program for insect flight Open
Patterns of motor activity can be used to decode behavior state. Precise spike timing encoding is present in many motor systems, but is not frequently utilized to decode behavior or to examine how coordination is achieved across many motor…
View article: Towards Explainable Convolutional Features for Music Audio Modeling.
Towards Explainable Convolutional Features for Music Audio Modeling. Open
Audio signals are often represented as spectrograms and treated as 2D images. In this light, deep convolutional architectures are widely used for music audio tasks even though these two data types have very different structures. In this wo…
View article: A Methodology for Exploring Deep Convolutional Features in Relation to Hand-Crafted Features with an Application to Music Audio Modeling
A Methodology for Exploring Deep Convolutional Features in Relation to Hand-Crafted Features with an Application to Music Audio Modeling Open
Understanding the features learned by deep models is important from a model trust perspective, especially as deep systems are deployed in the real world. Most recent approaches for deep feature understanding or model explanation focus on h…
View article: Task-Aware Neural Architecture Search
Task-Aware Neural Architecture Search Open
The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than traditional handcrafted design, although they require domain…
View article: Neural Architecture Search From Fréchet Task Distance.
Neural Architecture Search From Fréchet Task Distance. Open
We formulate a Frechet-type asymmetric distance between tasks based on Fisher Information Matrices. We show how the distance between a target task and each task in a given set of baseline tasks can be used to reduce the neural architecture…
View article: Improved Automated Machine Learning from Transfer Learning
Improved Automated Machine Learning from Transfer Learning Open
In this paper, we propose a neural architecture search framework based on a similarity measure between some baseline tasks and a target task. We first define the notion of the task similarity based on the log-determinant of the Fisher Info…
View article: Neural Architecture Search From Task Similarity Measure
Neural Architecture Search From Task Similarity Measure Open
In this paper, we propose a neural architecture search framework based on a similarity measure between various tasks defined in terms of Fisher information. By utilizing the relation between a target and a set of existing tasks, the search…
View article: Insights from macroevolutionary modelling and ancestral state reconstruction into the radiation and historical dietary ecology of Lemuriformes (Primates, Mammalia)
Insights from macroevolutionary modelling and ancestral state reconstruction into the radiation and historical dietary ecology of Lemuriformes (Primates, Mammalia) Open
The lemurs are a highly species-rich clade of primates, which, confined almost entirely to the island of Madagascar, have evolved to rival the diversity of rest of the primate order. We test the adaptive radiation model of Malagasy lemur d…
View article: Approximating the Riemannian Metric from Point Clouds via Manifold Moving Least Squares
Approximating the Riemannian Metric from Point Clouds via Manifold Moving Least Squares Open
The approximation of both geodesic distances and shortest paths on point cloud sampled from an embedded submanifold $\mathcal{M}$ of Euclidean space has been a long-standing challenge in computational geometry. Given a sampling resolution …
View article: GeoStat Representations of Time Series for Fast Classification
GeoStat Representations of Time Series for Fast Classification Open
Recent advances in time series classification have largely focused on methods that either employ deep learning or utilize other machine learning models for feature extraction. Though successful, their power often comes at the requirement o…
View article: An Interpretable Baseline for Time Series Classification Without Intensive Learning.
An Interpretable Baseline for Time Series Classification Without Intensive Learning. Open
Recent advances in time series classification have largely focused on methods that either employ deep learning or utilize other machine learning models for feature extraction. Though such methods have proven powerful, they can also require…
View article: Learning Partial Differential Equations From Data Using Neural Networks
Learning Partial Differential Equations From Data Using Neural Networks Open
We develop a framework for estimating unknown partial differential equations from noisy data, using a deep learning approach. Given noisy samples of a solution to an unknown PDE, our method interpolates the samples using a neural network, …
View article: Quantifying Gerrymandering in North Carolina
Quantifying Gerrymandering in North Carolina Open
By comparing a specific redistricting plan to an ensemble of plans, we evaluate whether the plan translates individual votes to election outcomes in an unbiased fashion. Explicitly, we evaluate if a given redistricting plan exhibits extrem…
View article: Prediction in Online Convex Optimization for Parametrizable Objective Functions
Prediction in Online Convex Optimization for Parametrizable Objective Functions Open
Many techniques for online optimization problems involve making decisions based solely on presently available information: fewer works take advantage of potential predictions. In this paper, we discuss the problem of online convex optimiza…
View article: A Distributed Online Convex Optimization Algorithm with Improved Dynamic Regret
A Distributed Online Convex Optimization Algorithm with Improved Dynamic Regret Open
In this paper, we consider the problem of distributed online convex optimization, where a network of local agents aim to jointly optimize a convex function over a period of multiple time steps. The agents do not have any information about …
View article: Distributed Online Convex Optimization with Improved Dynamic Regret
Distributed Online Convex Optimization with Improved Dynamic Regret Open
In this paper, we consider the problem of distributed online convex optimization, where a group of agents collaborate to track the global minimizers of a sum of time-varying objective functions in an online manner. Specifically, we propose…
View article: Eyes on the Prize: Improved Biological Surface Registration via Forward Propagation
Eyes on the Prize: Improved Biological Surface Registration via Forward Propagation Open
Many algorithms for surface registration risk producing significant errors if surfaces are significantly nonisometric. Manifold learning has been shown to be effective at improving registration quality, using information from an entire col…
View article: Eyes on the Prize: Improved Biological Surface Registration via Forward\n Propagation
Eyes on the Prize: Improved Biological Surface Registration via Forward\n Propagation Open
Many algorithms for surface registration risk producing significant errors if\nsurfaces are significantly nonisometric. Manifold learning has been shown to be\neffective at improving registration quality, using information from an entire\n…
View article: Evaluating Partisan Gerrymandering in Wisconsin
Evaluating Partisan Gerrymandering in Wisconsin Open
We examine the extent of gerrymandering for the 2010 General Assembly district map of Wisconsin. We find that there is substantial variability in the election outcome depending on what maps are used. We also found robust evidence that the …
View article: Redistricting: Drawing the Line
Redistricting: Drawing the Line Open
We develop methods to evaluate whether a political districting accurately represents the will of the people. To explore and showcase our ideas, we concentrate on the congressional districts for the U.S. House of representatives and use the…