Improving Generalization of Pretrained Language Models

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

Transformer models such as GPT generate human-like language and are predictive of human brain responses to language. Here, using functional-MRI-measured brain responses to 1,000 diverse sentences, we first show that a GPT-based encoding model can predict t ...

Throughout history, the pace of knowledge and information sharing has evolved into an unthinkable speed and media. At the end of the XVII century, in Europe, the ideas that would shape the "Age of Enlightenment" were slowly being developed in coffeehouses, ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

Proprioception tells the brain the state of the body based on distributed sensors in the body. However, the principles that govern proprioceptive processing from those distributed sensors are poorly understood. Here, we employ a task-driven neural network ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cu ...

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...

Recent advancements in deep learning have revolutionized 3D computer vision, enabling the extraction of intricate 3D information from 2D images and video sequences. This thesis explores the application of deep learning in three crucial challenges of 3D com ...

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can creat ...

The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

Efficient sampling and approximation of Boltzmann distributions involving large sets of binary variables, or spins, are pivotal in diverse scientific fields even beyond physics. Recent advances in generative neural networks have significantly impacted this ...

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

Dynamic aperture is an important concept for the study of non-linear beam dynamics in circular accelerators. It describes the extent of the phase-space region where a particle's motion remains bounded over a given number of turns. Understanding the feature ...

Improving Generalization of Pretrained Language Models

Chat with Graph Search

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Driving and suppressing the human language network using large language models

Machine Learning for Modeling Stock Returns

Topics in statistical physics of high-dimensional machine learning

Random matrix methods for high-dimensional machine learning models

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Understanding generalization and robustness in modern deep learning

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights

Robust machine learning for neuroscientific inference

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Efficient local linearity regularization to overcome catastrophic overfitting

Advancing Self-Supervised Deep Learning for 3D Scene Understanding

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Safe Deep Neural Networks

Sparse autoregressive neural networks for classical spin systems

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Optimizing Dynamic Aperture Studies with Active Learning