paper-with-me

Papers

SplineNets: Continuous Neural Decision Graphs

2018-10-31 · NeurIPS 2018 12 · Cem Keskin, Shahram Izadi

We present SplineNets, a practical and novel approach for using conditioning in convolutional neural networks (CNNs). SplineNets are continuous generalizations of neural decision graphs, and they can dramatically reduce runtime complexity and computation costs of CNNs, while maintaining or even increasing accuracy. Functions of SplineNets are both dynamic (i.e., conditioned on the input) and hierarchical (i.e., conditioned on the computational path). SplineNets employ a unified loss function with a desired level of smoothness over both the network and decision parameters, while allowing for sparse activation of a subset of nodes for individual samples. In particular, we embed infinitely many function weights (e.g. filters) on smooth, low dimensional manifolds parameterized by compact B-splines, which are indexed by a position parameter. Instead of sampling from a categorical distribution to pick a branch, samples choose a continuous position to pick a function weight. We further show that by maximizing the mutual information between spline positions and class labels, the network can be optimally utilized and specialized for classification tasks. Experiments show that our approach can significantly increase the accuracy of ResNets with negligible cost in speed, matching the precision of a 110 level ResNet with a 32 level SplineNet.

📄 PDF Abstract BibTeX arXiv:1810.13118

Code (0)

등록된 구현이 없습니다.

Tasks

Position

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Kaiming Initialization 설명 없음

Similar Papers 제목 키워드 기반

Learning Efficient Surrogate Dynamic Models with Graph Spline Networks

2023-10-25 · NeurIPS 2023 11 · Chuanbo Hua, Federico Berto, Michael Poli, Stefano Massaroli 외

While complex simulations of physical systems have been widely used in engineering and scientific computing, lowering their often prohibitive computational requirements has only recently been tackled by deep learning app…

Deep Learning

Flowsheet synthesis through hierarchical reinforcement learning and graph neural networks

2022-07-25 · Laura Stops, Roel Leenhouts, Qinghe Gao, Artur M. Schweidtmann

Process synthesis experiences a disruptive transformation accelerated by digitization and artificial intelligence. We propose a reinforcement learning algorithm for chemical process design based on a state-of-the-art act…

Chemical ProcessDecision MakingHierarchical Reinforcement Learningreinforcement-learning+2

A Tutorial for Weighted Bipolar Argumentation with Continuous Dynamical Systems and the Java Library Attractor

2018-11-30 · Nico Potyka

Weighted bipolar argumentation frameworks allow modeling decision problems and online discussions by defining arguments and their relationships. The strength of arguments can be computed based on an initial weight and th…

Skill Discovery for Exploration and Planning using Deep Skill Graphs

2020-06-12 · ICML Workshop LifelongML 2020 7 · Akhil Bagaria, Jason Crowley, Jing Wei Nicholas Lim, George Konidaris

Temporal abstraction provides an opportunity to drastically lower the decision making burden facing reinforcement learning agents in rich sensorimotor spaces. Well constructed hierarchies induce state and action abstrac…

continuous-controlContinuous ControlDecision Making

Right Place, Right Time! Dynamizing Topological Graphs for Embodied Navigation

2024-03-14 · Vishnu Sashank Dorbala, Bhrij Patel, Amrit Singh Bedi, Dinesh Manocha

Embodied Navigation tasks often involve constructing topological graphs of a scene during exploration to facilitate high-level planning and decision-making for execution in continuous environments. Prior literature makes…

Decision MakingLanguage ModelingLanguage ModellingLarge Language Model+2