| 1 |
Chess AI: Competing Paradigms for Machine Intelligence
|
|
|
|
In: Entropy; Volume 24; Issue 4; Pages: 550 (2022)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Inductive Bias and Modular Design for Sample-Efficient Neural Language Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
PSINES: Activity and Availability Prediction for Adaptive Ambient Intelligence
|
|
|
|
In: ISSN: 1556-4665 ; EISSN: 1556-4703 ; ACM Transactions on Autonomous and Adaptive Systems ; https://hal.archives-ouvertes.fr/hal-02943970 ; ACM Transactions on Autonomous and Adaptive Systems, Association for Computing Machinery (ACM), 2020, 15 (1), pp.1-12. ⟨10.1145/3424344⟩ (2020)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Analyzing Uncertainty in Complex Socio-Ecological Networks
|
|
|
|
In: Entropy ; Volume 22 ; Issue 1 (2020)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Inductive Bias and Modular Design for Sample-Efficient Neural Language Learning
|
|
|
|
Abstract:
Most of the world's languages suffer from the paucity of annotated data. This curbs the effectiveness of supervised learning, the most widespread approach to modelling language. Instead, an alternative paradigm could take inspiration from the propensity of children to acquire language from limited stimuli, in order to enable machines to learn any new language from a few examples. The abstract mechanisms underpinning 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 both these intuitions. Firstly, I argue that endowing a neural network with the correct inductive biases is equivalent to constructing a prior distribution over its weights and its architecture (including connectivity patterns and non-linear activations). This prior is inferred by "reverse-engineering" a representative set of observed languages and harnessing typological features documented by linguists. Thus, I provide a unified framework for cross-lingual transfer and architecture search by recasting them as hierarchical Bayesian neural models. Secondly, the skills relevant to different language varieties and different tasks in natural language processing are deeply intertwined. Hence, the neural weights modelling the data for each of their combinations can be imagined as lying in a structured space. I introduce a Bayesian generative model of this space, which is factorised into latent variables representing each language and each task. By virtue of this modular design, predictions can generalise to unseen combinations by extrapolating from the data of observed combinations. The proposed models are empirically validated on a spectrum of language-related tasks (character-level language modelling, part-of-speech tagging, named entity recognition, and common-sense reasoning) and a typologically diverse sample of about a hundred languages. Compared to a series of competitive baselines, they achieve better performances in new languages in zero-shot and few-shot learning settings. In general, they hold promise to extend state-of-the-art language technology to under-resourced languages by means of sample efficiency and robustness to the cross-lingual variation. ; ERC (Consolidator Grant 648909) Lexical Google Research Faculty Award 2018
|
|
Keyword:
Bayesian Models; Deep Learning; Inductive Bias; Linguistic Typology; Modularity; Multilingual Natural Language Processing; Neural Networks; Sample Efficiency; Systematic Generalisation
|
|
URL: https://doi.org/10.17863/CAM.66424
https://www.repository.cam.ac.uk/handle/1810/319303
|
|
BASE
|
|
Hide details
|
|
|
| 7 |
Face Perception: The Interaction of Eye Movements with Internal Face Representations
|
|
Tsank, Yuliy. - : eScholarship, University of California, 2019
|
|
BASE
|
|
Show details
|
|
|
| 8 |
Modelling Dependency Structures Produced by the Introduction of a Flipped Classroom
|
|
|
|
In: Mathematics ; Volume 8 ; Issue 1 (2019)
|
|
BASE
|
|
Show details
|
|
|
| 9 |
Data Fusion through Fuzzy-Bayesian Networks for Belief Generation in Cognitive Agents
|
|
|
|
In: Revista de Informática Teórica e Aplicada; v. 26, n. 2 (2019); 69-80 ; 21752745 ; 01034308 (2019)
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Decision fusion dedicated to the monitoring of complex systems ; Fusion de décisions dédiée à la surveillance des systèmes complexes
|
|
|
|
In: https://tel.archives-ouvertes.fr/tel-02130706 ; Génie des procédés. Université d'Angers, 2018. Français. ⟨NNT : 2018ANGE0014⟩ (2018)
|
|
BASE
|
|
Show details
|
|
|
| 11 |
Intrinsic Properties of tRNA Molecules as Deciphered via Bayesian Network and Distribution Divergence Analysis
|
|
|
|
In: Life; Volume 8; Issue 1; Pages: 5 (2018)
|
|
BASE
|
|
Show details
|
|
|
| 12 |
Fuzzy-Based Risk Analysis for IT-Systems and Their Infrastructure ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 13 |
Knowledge-Based Probabilistic Modeling For Tracking Lyrics In Music Audio Signals ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Knowledge-Based Probabilistic Modeling For Tracking Lyrics In Music Audio Signals ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Affective learning: improving engagement and enhancing learning with affect-aware feedback
|
|
|
|
In: User Modeling and User-Adapted Interaction pp. 1-40. (2017) (In press). (2017)
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Sequential estimation techniques and application to multiple speaker tracking and language modeling
|
|
Oualil, Youssef. - : Saarländische Universitäts- und Landesbibliothek, 2017
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Knowledge-based probabilistic modeling for tracking lyrics in music audio signals
|
|
|
|
In: TDX (Tesis Doctorals en Xarxa) (2017)
|
|
BASE
|
|
Show details
|
|
|
| 19 |
Risk analysis with a fuzzy-logic approach of a complex installation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
