Search Results for author:
Found 26 papers, 6 papers with code
Soft-Label Dataset Distillation and Text Dataset Distillation
We propose to simultaneously distill both images and their labels, thus assigning each synthetic sample a `soft' label (a distribution of labels).
'Less Than One'-Shot Learning: Learning N Classes From M<N Samples
We propose the `less than one'-shot learning task where models must learn $N$ new classes given only $M<N$ examples and we show that this is achievable with the help of soft labels.
Optimal 1-NN Prototypes for Pathological Geometries
Using prototype methods to reduce the size of training datasets can drastically reduce the computational cost of classification with instance-based learning algorithms like the k-Nearest Neighbour classifier.
One Line To Rule Them All: Generating LO-Shot Soft-Label Prototypes
We propose a novel, modular method for generating soft-label prototypical lines that still maintains representational accuracy even when there are fewer prototypes than the number of classes in the data.
SecDD: Efficient and Secure Method for Remotely Training Neural Networks
We leverage what are typically considered the worst qualities of deep learning algorithms - high computational cost, requirement for large data, no explainability, high dependence on hyper-parameter choice, overfitting, and vulnerability to adversarial perturbations - in order to create a method for the secure and efficient training of remotely deployed neural networks over unsecured channels.
Human-in-the-Loop Mixup
We focus on the synthetic data used in mixup: a powerful regularizer shown to improve model robustness, generalization, and calibration.
Deep Learning for System Trace Restoration
The output of the model will be a close reconstruction of the true data, and can be fed to algorithms that rely on clean data.
Can Humans Do Less-Than-One-Shot Learning?
Being able to learn from small amounts of data is a key characteristic of human intelligence, but exactly {\em how} small?
Predicting Human Similarity Judgments Using Large Language Models
Similarity judgments provide a well-established method for accessing mental representations, with applications in psychology, neuroscience and machine learning.
Words are all you need? Language as an approximation for human similarity judgments
Based on the results of this comprehensive study, we provide a concise guide for researchers interested in collecting or approximating human similarity data.
Analyzing Diffusion as Serial Reproduction
Diffusion models are a class of generative models that learn to synthesize samples by inverting a diffusion process that gradually maps data into noise.
On the Informativeness of Supervision Signals
Supervised learning typically focuses on learning transferable representations from training examples annotated by humans.
Large language models predict human sensory judgments across six modalities
Determining the extent to which the perceptual world can be recovered from language is a longstanding problem in philosophy and cognitive science.
Around the world in 60 words: A generative vocabulary test for online research
Six behavioral experiments (N=236) in six countries and eight languages show that (a) our test can distinguish between native speakers of closely related languages, (b) the test is reliable ($r=0. 82$), and (c) performance strongly correlates with existing tests (LexTale) and self-reports.
Human Uncertainty in Concept-Based AI Systems
We study how existing concept-based models deal with uncertain interventions from humans using two novel datasets: UMNIST, a visual dataset with controlled simulated uncertainty based on the MNIST dataset, and CUB-S, a relabeling of the popular CUB concept dataset with rich, densely-annotated soft labels from humans.
Getting aligned on representational alignment
Finally, we lay out open problems in representational alignment where progress can benefit all three of these fields.
Dimensions of Disagreement: Unpacking Divergence and Misalignment in Cognitive Science and Artificial Intelligence
The increasing prevalence of artificial agents creates a correspondingly increasing need to manage disagreements between humans and artificial agents, as well as between artificial agents themselves.
Concept Alignment as a Prerequisite for Value Alignment
Value alignment is essential for building AI systems that can safely and reliably interact with people.
Learning Human-like Representations to Enable Learning Human Values
We propose that this kind of representational alignment between machine learning (ML) models and humans can also support value alignment, allowing ML systems to conform to human values and societal norms.
Concept Alignment
Discussion of AI alignment (alignment between humans and AI systems) has focused on value alignment, broadly referring to creating AI systems that share human values.
Preference-Conditioned Language-Guided Abstraction
We observe that how humans behave reveals how they see the world.
Measuring Implicit Bias in Explicitly Unbiased Large Language Models
Large language models (LLMs) can pass explicit bias tests but still harbor implicit biases, similar to humans who endorse egalitarian beliefs yet exhibit subtle biases.
A Rational Analysis of the Speech-to-Song Illusion
Here we provide a formal account of this phenomenon, by recasting it as a statistical inference whereby a rational agent attempts to decide whether a sequence of utterances is more likely to have been produced in a song or speech.
Learning with Language-Guided State Abstractions
We describe a framework for using natural language to design state abstractions for imitation learning.
Large language models surpass human experts in predicting neuroscience results
LLMs trained on the vast scientific literature could potentially integrate noisy yet interrelated findings to forecast novel results better than human experts.
Analyzing the Roles of Language and Vision in Learning from Limited Data
Does language help make sense of the visual world?
