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 66 for “"Neural models"”.
-
Disentangled representations in neural models
… is the foundation for the recent success of neural network models. However, the distributed representations generated by neural networks are far from ideal. Due to their highly entangled nature, they are difficult to reuse and interpret, and they do a poor job of capturing the sparsity which …
-
Interpretable neural models for natural language processing
The success of neural network models often comes at a cost of interpretability. This thesis addresses the problem by providing justifications behind the model's structure and predictions. In the first part of this thesis, we present a class of sequence operations for text processing. The proposed …
-
Learning and memory in chaotic spiking neural models
… has been done in the context of chaotic spiking neural networks (CSNNs). Chaos provides many interesting properties that can be used to achieve computational tasks. Such properties are sensitivity to initial conditions, space filling, control and synchronization. Biological research suggests that …
-
Greedy Inference Algorithms for Structured and Neural Models
… multiple top-scoring hypotheses from structured (neural) models: 1) Entropy estimation. We aim to find deterministic samples that are representative of Gibbs distribution via a greedy strategy. 2) Searching for a set of diverse and high-quality bounding boxes. We formulate this problem as the …
-
Complexity Scaling Laws for Neural Models using Combinatorial Optimization
Recent work on neural scaling laws demonstrates that model performance scales predictably with compute budget, model size, and dataset size. In this work, we develop scaling laws based on problem complexity. We analyze two fundamental complexity measures: solution space size and representation …
-
The functionality of spatial and time domain artificial neural models.
… Artificial Intelligence systems. Artificial Neural Networks form the foundation of the research and their units, Artificial Neurons, are first compared with alternative models. This initial work is mainly in the spatial-domain and introduces a new neural model, termed a Taylor Series neuron. …
-
Noise-induced phenomena of signal transmission in excitable neural models
Meine Dissertation behandelt verschiedene neue rauschinduzierte Phänomene in anregbaren Neuronenmodellen, insbesondere solche mit FitzHugh-Nagumo Dynamik. Ich beschreibe das Auftreten von vibronischer Resonanz in anregbaren Systemen. Sowohl in einer anregbaren elektronischen Schaltung als auch im …
-
Neural models of modulation frequency analysis in the auditory system
… auditory system. A biologically motivated neural model of AM processing has been developed. The first main component of the model allows for the simulation of the response properties of cochlear nucleus ideal onset units, a neuron type that is known to encode the modulation frequency of AM …
-
Combating fake news with adversarial domain adaptation and neural models
… Short Term Memory (Bi-LSTM) and Convolutional Neural Network (CNN) based models and conduct our experiments on the LIAR dataset [Wang, 2017], a recently released fact checking task. Our model outperforms the state of the art baseline on this dataset. For the stance detection task, we present …
-
Biologically inspired computational neural models for motivated behavior, learning, and memory
… is to introduce a set of biologically inspired models for motivated behavior, learning, and memory, that can be incorporated into artificially intelligent agents and networks. These models may also provide insights into the biological processes of episodic memory, aesthetics, and complex …
-
Development of Adaptive and Factorized Neural Models for MPC of Industrial Systems
… of adaptive and factorized RBF network models. Model predictive control (MPC) based on the factorized RBF model is applied to a non-linear proton exchange membrane fuel cell (PEMFC) stack system. The main contents include three parts: RBF model adaptation; model factorization and fast …
-
Learning sentiment and semantic relatedness in user generated content using neural models
… trends of deep learning, this work applies neural networks to solve these tasks. We design neuralbased models including Convolutional Neural Networks (CNNs) and Long Short-Term Memory Networks (LSTMs) to capture the semantic and sentiment information. Aspect Based Sentiment Analysis is …
-
Advanced Bioelectronic and Microphysiological Systems for Functional Studies of Stem Cell-Derived Neural Models
… functional interrogation of stem cell-derived neural models. Motivated by the staggering failure rate (exceeding 90%) of neurological drug candidates in clinical trials, the work addresses limitations in preclinical modelling by combining advanced microfabrication, flexible electronics, and …
-
Restoring the Balance: Unraveling disease mechanisms and exploring shared therapies for lysine metabolism disorders using human neural models
Contains fulltext : 329214.pdf (Publisher’s version ) (Closed access)
-
SYMBOLIC AND NEURAL APPROACHES TO NATURAL LANGUAGE INFERENCE
… studies have proposed logic-based, symbolic models and neural network models to perform inference. However, in the symbolic tradition, relatively few systems are designed based on monotonicity and natural logic rules; in the neural network tradition, most work is focused exclusively on …
-
Weakly-supervised text classification
Deep neural networks are gaining increasing popularity for the classic text classification task, due to their strong expressive power and less requirement for feature engineering. Despite such attractiveness, neural text classification models suffer from the lack of training data in many real-world …
-
Improving neural language models on low-resource creole languages
When using neural models for NLP tasks, like language modelling, it is difficult to utilize a language with little data, also known as a low-resource language. Creole languages are frequently low-resource and as such it is difficult to train neural language models for them well. Creole languages …
-
Compositional Models for Few Shot Sequence Learning
Flexible neural sequence models outperform grammar- and automaton-based counterparts on a variety of tasks. However, neural models perform poorly in settings requiring compositional generalization beyond the training data—particularly to rare or unseen subsequences. Past work has found symbolic …
-
HiBi: A hierarchical bigram model for associative learning
… people gradually abandon traditional statistical models in favor of deep neural architectures. While effective in learning input-output mappings from two arbitrary distributions, the complex nature of neural models makes them hard to interpret. In this thesis, we introduce a more interpretable …
-
Enhanced knowledge distillation by auxiliary classifiers
Deep neural models have shown promising results in various areas, e.g., computer vision and natural language processing, at the cost of high computation and storage resource consumption. These characteristics of deep neural networks have acted as a barrier in resource-constraint environments, e.g., …
Page 1 of 4