93 citations · 153 across the 18 of their papers we have counts for
12 papers · 1 filter
Alignment with human representations supports robust few-shot learning
Ilia Sucholutsky, Thomas L. Griffiths
Should we care whether AI systems have representations of the world that are similar to those of humans? We provide an information-theoretic analysis that suggests that there shoul…
On the Informativeness of Supervision Signals
Ilia Sucholutsky, Ruairidh M. Battleday, Katherine M. Collins +7
Supervised learning typically focuses on learning transferable representations from training examples annotated by humans. While rich annotations (like soft labels) carry more info…
Human-in-the-Loop Mixup
Katherine M. Collins, Umang Bhatt, Weiyang Liu +4
Aligning model representations to humans has been found to improve robustness and generalization. However, such methods often focus on standard observational data. Synthetic data i…
Analyzing Diffusion as Serial Reproduction
Raja Marjieh, Ilia Sucholutsky, Thomas A. Langlois +2
Diffusion models are a class of generative models that learn to synthesize samples by inverting a diffusion process that gradually maps data into noise. While these models have enj…
Predicting Human Similarity Judgments Using Large Language Models
Raja Marjieh, Ilia Sucholutsky, Theodore R. Sumers +2
Similarity judgments provide a well-established method for accessing mental representations, with applications in psychology, neuroscience and machine learning. However, collecting…
Can Humans Do Less-Than-One-Shot Learning?
Maya Malaviya, Ilia Sucholutsky, Kerem Oktar +1
Being able to learn from small amounts of data is a key characteristic of human intelligence, but exactly {\em how} small? In this paper, we introduce a novel experimental paradigm…
One Line To Rule Them All: Generating LO-Shot Soft-Label Prototypes
Ilia Sucholutsky, Nam-Hwui Kim, Ryan P. Browne +1
Increasingly large datasets are rapidly driving up the computational costs of machine learning. Prototype generation methods aim to create a small set of synthetic observations tha…
Optimal 1-NN Prototypes for Pathological Geometries
Ilia Sucholutsky, Matthias Schonlau
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-N…
SecDD: Efficient and Secure Method for Remotely Training Neural Networks
Ilia Sucholutsky, Matthias Schonlau
We leverage what are typically considered the worst qualities of deep learning algorithms - high computational cost, requirement for large data, no explainability, high dependence…
'Less Than One'-Shot Learning: Learning N Classes From M<N Samples
Ilia Sucholutsky, Matthias Schonlau
Deep neural networks require large training sets but suffer from high computational cost and long training times. Training on much smaller training sets while maintaining nearly th…
Soft-Label Dataset Distillation and Text Dataset Distillation
Ilia Sucholutsky, Matthias Schonlau
Dataset distillation is a method for reducing dataset sizes by learning a small number of synthetic samples containing all the information of a large dataset. This has several bene…
Deep Learning for System Trace Restoration
Ilia Sucholutsky, Apurva Narayan, Matthias Schonlau +1
Most real-world datasets, and particularly those collected from physical systems, are full of noise, packet loss, and other imperfections. However, most specification mining, anoma…