Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 41 for “"Inductive Bias"”.
-
On Principled Modeling of Inductive Bias in Machine Learning
The inductive bias of a learning algorithm is the set of assumptions that the hypothesis uses to predict unseen data, governing its generalization power. This thesis focuses on principled approaches to modeling inductive bias of learning algorithms. We start with a unifying view on inductive bias …
-
Inductive Bias and Modular Design for Sample-Efficient Neural Language Learning
… this ability include 1) a set of in-born inductive biases and 2) the deep entrenchment of language in other perceptual and cognitive faculties, combined with the ability to transfer and recombine knowledge across these domains. The main contribution of my thesis is giving concrete form to …
-
Deep neural networks are lazy : on the inductive bias of deep learning
… that deep neural networks have an inherent inductive bias that makes them inclined to learn generalizable hypotheses and avoid memorization. In this respect, we propose results that suggest that the inductive bias stems from neural networks being lazy: they tend to learn simpler rules first. …
-
Towards High-Dimensional Generalization in Neural Networks
… scaling laws with respect to training time. 2. Inductive bias refers to the set of assumptions a learning algorithm makes to predict outputs on inputs it has not encountered. We propose quantifying the amount of inductive bias required for a model to generalize well with a fixed amount of …
-
Predictive Models for Visuomotor Feedback Control in Object Pile Manipulation
… we analyze and describe the reason for this inductive bias of linear models by describing the pixel space as a space of measures, and show limitations of this approach outside of object pile manipulation. In the final chapter of this thesis, we present a more general solution to image-based …
-
A spatial deep network architecture for brain decoding
… across layers based on spatial similarity. The inductive bias of structured smoothness implemented by FGL is motivated by applications such as brain image decoding, i.e., predicting behavior based on brain images, where scientific prior knowledge suggests that brain responses conditioned on …
-
Use-driven concept formation
… domain-specific concepts, including a new inductive bias that I call the equivalence class principle. I then use the domain of two-player, perfect-information games to test and refine those principles. I show how the principles can be applied in a semiautomated fashion to identify …
-
Injecting Inductive Biases into Distributed Representations of Text
… the desired properties into embeddings, use inductive biases. First, we use Knowledge Graphs (KGs) as a data-based inductive bias to derive the semantic representation of words and sentences. The explicit semantics that is encoded in a structure of a KG allows us to acquire the semantic …
-
Inductive Biases and Generalisation in Models for Natural Language Processing
… model architectures with carefully considered inductive biases might lead to improved data-efficiency and performance, by nudging them towards solutions of particular forms and enabling them to generalise from small amounts of data in a more human-like way. This thesis describes work which …
-
Towards More Generalizable Neural Networks via Modularity
… task as the amount of information content in the inductive biases required to solve a task, and demonstrates that generalization difficulty relies crucially on the number of dimensions of generalization. Inspired by the modularity of biological learning systems, this thesis then demonstrates …
-
Disentangling neural network representations for improved generalization
… in data collection and model design. Generally, inductive biases can make this process easier by leveraging knowledge about the world to guide neural network design. One such inductive bias is disentanglment, which can help preven neural networks from learning representations that capture …
-
Physical symmetry enhanced neural networks
… method to extend convolutional neural networks' inductive bias and embed other types of symmetries. We show that this method improves prediction performance on lens-distorted image
-
Single-Model Any-Subgroup Equivariance via Symmetric Positional Encodings
The inclusion of symmetries as an inductive bias, known as “equivariance”, often improves generalization on geometric data (e.g. grids, sets, and graphs). However, equivariant architectures are usually highly constrained, designed for pre-chosen symmetries, and cannot be applied to datasets with …
-
Anomaly Detection in Collider Physics via Factorized Observables
… expectations. Our approach is based on the inductive bias of factorization, which is the idea that the physics governing different energy scales can be treated as approximately independent. Assuming factorization holds separately for signal and background processes, the appearance of …
-
Algorithms for learning to induce programs
… of all programs is infinite, so we need a strong inductive bias or prior to steer us toward the correct programs; and even if we have that prior, effectively searching through the vast combinatorial space of all programs is generally intractable. We introduce algorithms that learn to induce …
-
Trainable Pre-Filtering for Deep Neural Networks and Applications
… the learning pipeline, introducing explicit inductive bias while preserving end-to-end optimization. The proposed approach is validated across multiple real-world applications, including infrared air-leak identification, adversarially robust image classification, power line monitoring, and …
-
Parsimonious Principles of Deep Neural Networks
… this thesis, we explore the intrinsic simplicity bias exhibited by deep neural networks — the powerhouse of modern AI. By analyzing the effective rank of the learned representation kernels, we unveil the observation that these models have an inherent preference for learning parsimonious …
-
Modeling the Geometry of Neural Network Representation Spaces
… arising in physical data, providing a powerful inductive bias for learning. Specifically, we use geometric spaces such as the real projective plane and the spectraplex to build a) provably powerful neural networks that respect the symmetries of eigenvectors, which is important for building …
-
Learning compositional dynamics models for model-based control
… the particle-based representation poses strong inductive bias for learning: particles of the same type have the same dynamics within. We demonstrate that our models not only outperform current learnable physics engines in forward simulation, but also achieve superior performance on various …
-
Neural language models and human linguistic knowledge
… generalizations depend more on a learner's inductive bias than on training data size. Second, I use LMs to explain systematic variation in scalar inferences by approximating human listeners' expectations over unspoken alternative sentences (e.g., "The bill was supported overwhelmingly" …
Page 1 of 3