Search Results for author:
Found 28 papers, 13 papers with code
Adaptive XGBoost for Evolving Data Streams
The proposed method creates new members of the ensemble from mini-batches of data as new data becomes available.
Regularisation of Neural Networks by Enforcing Lipschitz Continuity
We investigate the effect of explicitly enforcing the Lipschitz continuity of neural networks with respect to their inputs.
PolyLM: Learning about Polysemy through Language Modeling
To avoid the "meaning conflation deficiency" of word embeddings, a number of models have aimed to embed individual word senses.
A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal
Despite its strong empirical performance, rehearsal methods still suffer from a poor approximation of the loss landscape of past data with memory samples.
Stochastic Gradient Trees
We present an algorithm for learning decision trees using stochastic gradient information as the source of supervision.
Semi-Supervised Learning using Siamese Networks
This work explores a new training method for semi-supervised learning that is based on similarity function learning using a Siamese network to obtain a suitable embedding.
Better Self-training for Image Classification through Self-supervision
Self-training is a simple semi-supervised learning approach: Unlabelled examples that attract high-confidence predictions are labelled with their predictions and added to the training set, with this process being repeated multiple times.
Transfer of Pretrained Model Weights Substantially Improves Semi-Supervised Image Classification
Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training.
Seeing The Whole Patient: Using Multi-Label Medical Text Classification Techniques to Enhance Predictions of Medical Codes
We also show that high dimensional embeddings pre-trained using health-related data present a significant improvement in a multi-label setting, similarly to the way they improve performance for binary classification.
Improving Predictions of Tail-end Labels using Concatenated BioMed-Transformers for Long Medical Documents
Improving the tail-end label predictions in multi-label classifications of medical text enables the potential to understand patients better and improve care.
MaxGain: Regularisation of Neural Networks by Constraining Activation Magnitudes
Effective regularisation of neural networks is essential to combat overfitting due to the large number of parameters involved.
Building Ensembles of Adaptive Nested Dichotomies with Random-Pair Selection
A system of nested dichotomies is a method of decomposing a multi-class problem into a collection of binary problems.
Fast Metric Learning For Deep Neural Networks
Similarity metrics are a core component of many information retrieval and machine learning systems.
Use of Ensembles of Fourier Spectra in Capturing Recurrent Concepts in Data Streams
In this research, we apply ensembles of Fourier encoded spectra to capture and mine recurring concepts in a data stream environment.
Probability Calibration Trees
Obtaining accurate and well calibrated probability estimates from classifiers is useful in many applications, for example, when minimising the expected cost of classifications.
On the Calibration of Nested Dichotomies for Large Multiclass Tasks
Nested dichotomies are used as a method of transforming a multiclass classification problem into a series of binary problems.
Ensembles of Nested Dichotomies with Multiple Subset Evaluation
A system of nested dichotomies is a method of decomposing a multi-class problem into a collection of binary problems.
A survey of automatic de-identification of longitudinal clinical narratives
Use of medical data, also known as electronic health records, in research helps develop and advance medical science.
Automatic end-to-end De-identification: Is high accuracy the only metric?
De-identification of electronic health records (EHR) is a vital step towards advancing health informatics research and maximising the use of available data.
Classifier Chains: A Review and Perspectives
This performance led to further studies of how exactly it works, and how it could be improved, and in the recent decade numerous studies have explored classifier chains mechanisms on a theoretical level, and many improvements have been made to the training and inference procedures, such that this method remains among the state-of-the-art options for multi-label learning.
Machine Learning (In) Security: A Stream of Problems
Machine Learning (ML) has been widely applied to cybersecurity and is considered state-of-the-art for solving many of the open issues in that field.
Predicting COVID-19 Patient Shielding: A Comprehensive Study
This study focuses on techniques used for the multi-label classification of medical text.
Closed-loop Control for Online Continual Learning
To address the non-stationarity in the continual learning environment, we employ a Q function with task-specific and task-shared components to support fast adaptation.
Improving the performance of bagging ensembles for data streams through mini-batching
This paper proposes a mini-batching strategy that can improve memory access locality and performance of several ensemble algorithms for stream mining in multi-core environments.
Balancing Performance and Energy Consumption of Bagging Ensembles for the Classification of Data Streams in Edge Computing
Such strategies can significantly reduce energy consumption in 96% of the experimental scenarios evaluated.
Feature Extractor Stacking for Cross-domain Few-shot Learning
Recently published CDFSL methods generally construct a universal model that combines knowledge of multiple source domains into one feature extractor.
Look At Me, No Replay! SurpriseNet: Anomaly Detection Inspired Class Incremental Learning
A common solution to both problems is "replay," where a limited buffer of past instances is utilized to learn cross-task knowledge and mitigate catastrophic interference.
