相关论文: Representation Matters: Assessing the Importance o…

Ensembles depend on diversity for improved performance. Many ensemble training methods, therefore, attempt to optimize for diversity, which they almost always define in terms of differences in training set predictions. In this paper,…

Cognitive neuroscience is enjoying rapid increase in extensive public brain-imaging datasets. It opens the door to large-scale statistical models. Finding a unified perspective for all available data calls for scalable and automated…

Data heterogeneity is a prevalent issue, stemming from various conflicting factors, making its utilization complex. This uncertainty, particularly resulting from disparities in data formats, frequently necessitates the involvement of…

Work in cognitive science and artificial intelligence has suggested that exposing learning agents to traces of interaction between multiple individuals can improve performance in a variety of settings, yet it remains unknown which features…

We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition. We build our method on Transformers for its efficacy. Although we have witnessed great progress for video action…

Projecting high-dimensional environment observations into lower-dimensional structured representations can considerably improve data-efficiency for reinforcement learning in domains with limited data such as robotics. Can a single generally…

As the number of applications that use machine learning algorithms increases, the need for labeled data useful for training such algorithms intensifies. Getting labels typically involves employing humans to do the annotation, which directly…

Achieving human-level translations requires leveraging context to ensure coherence and handle complex phenomena like pronoun disambiguation. Sparsity of contextually rich examples in the standard training data has been hypothesized as the…

Reinforcement learning (RL) agents make decisions using nothing but observations from the environment, and consequently, heavily rely on the representations of those observations. Though some recent breakthroughs have used vector-based…

In semi-supervised representation learning frameworks, when the number of labelled data is very scarce, the quality and representativeness of these samples become increasingly important. Existing literature on semi-supervised learning…

Recently, in the area of big data, some popular applications such as web search engines and recommendation systems, face the problem to diversify results during query processing. In this sense, it is both significant and essential to…

Data inherently possesses dual attributes: samples and targets. For targets, knowledge distillation has been widely employed to accelerate model convergence, primarily relying on teacher-generated soft target supervision. Conversely, recent…

We examine the influence of input data representations on learning complexity. For learning, we posit that each model implicitly uses a candidate model distribution for unexplained variations in the data, its noise model. If the model…

Joint machine learning models that allow synthesizing and classifying data often offer uneven performance between those tasks or are unstable to train. In this work, we depart from a set of empirical observations that indicate the…

In conventional deep learning, the number of neurons typically remains fixed during training. However, insights from biology suggest that the human hippocampus undergoes continuous neuron generation and pruning of neurons over the course of…

This dissertation establishes the contexture theory to mathematically characterize the mechanism of representation learning, or pretraining. Despite the remarkable empirical success of foundation models, it is not very clear what…

Deep Learning models have transformed various domains, including the healthcare sector, particularly biomedical image classification by learning intricate features and enabling accurate diagnostics pertaining to complex diseases. Recent…

Many machine learning algorithms represent input data with vector embeddings or discrete codes. When inputs exhibit compositional structure (e.g. objects built from parts or procedures from subroutines), it is natural to ask whether this…

Accurate trajectory prediction is critical for safe autonomous navigation, yet the impact of dataset design on model performance remains understudied. This work systematically examines how feature selection, cross-dataset transfer, and…

Instruction tuning is a vital step of training large language models (LLMs), so how to enhance the effect of instruction tuning has received increased attention. Existing works indicate that the quality of the dataset is more crucial than…