相关论文: PURE: Turning Polysemantic Neurons Into Pure Featu…

Modern deep learning algorithms tend to optimize an objective metric, such as minimize a cross entropy loss on a training dataset, to be able to learn. The problem is that the single metric is an incomplete description of the real world…

Brain decoding is a field of computational neuroscience that uses measurable brain activity to infer mental states or internal representations of perceptual inputs. Therefore, we propose a novel approach to brain decoding that also relies…

A central goal for mechanistic interpretability has been to identify the right units of analysis in large language models (LLMs) that causally explain their outputs. While early work focused on individual neurons, evidence that neurons…

Deep neural networks excel at finding hierarchical representations that solve complex tasks over large data sets. How can we humans understand these learned representations? In this work, we present network dissection, an analytic framework…

MRI-based modeling of brain networks has been widely used to understand functional and structural interactions and connections among brain regions, and factors that affect them, such as brain development and disease. Graph mining on brain…

Deep learning stands as the modern paradigm for solving cognitive tasks. However, as the problem complexity increases, models grow deeper and computationally prohibitive, hindering advancements in real-world and resource-constrained…

This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., explaining knowledge representations hidden in middle conv-layers of the CNN.…

Deep neural networks, in particular convolutional neural networks, have become highly effective tools for compressing images and solving inverse problems including denoising, inpainting, and reconstruction from few and noisy measurements.…

Due to the low signal-to-noise ratio and limited resolution of functional MRI data, and the high complexity of natural images, reconstructing a visual stimulus from human brain fMRI measurements is a challenging task. In this work, we…

Translating neural networks from theory to clinical practice has unique challenges, specifically in the field of neuroimaging. In this paper, we present DeepNeuro, a deep learning framework that is best-suited to putting deep learning…

Disentangling polysemantic neurons is at the core of many current approaches to interpretability of large language models. Here we attempt to study how disentanglement can be used to understand performance, particularly under weight…

It has long been speculated that deep neural networks function by discovering a hierarchical set of domain-specific core concepts or patterns, which are further combined to recognize even more elaborate concepts for the classification or…

Deep convolutional neural networks (CNNs) for image denoising have recently attracted increasing research interest. However, plain networks cannot recover fine details for a complex task, such as real noisy images. In this paper, we…

A central goal of interpretability is to recover representations of causally relevant concepts from the activations of neural networks. The quality of these concept representations is typically evaluated in isolation, and under implicit…

In current practice, many image processing tasks are done sequentially (e.g. denoising, dehazing, followed by semantic segmentation). In this paper, we propose a novel multi-task neural network architecture designed for combining sequential…

Deep neural networks are representation learning techniques. During training, a deep net is capable of generating a descriptive language of unprecedented size and detail in machine learning. Extracting the descriptive language coded within…

The advancement of robots, particularly those functioning in complex human-centric environments, relies on control solutions that are driven by machine learning. Understanding how learning-based controllers make decisions is crucial since…

Electron microscopic connectomics is an ambitious research direction with the goal of studying comprehensive brain connectivity maps by using high-throughput, nano-scale microscopy. One of the main challenges in connectomics research is…

Semantic image segmentation is a fundamental task in image understanding. Per-pixel semantic labelling of an image benefits greatly from the ability to consider region consistency both locally and globally. However, many Fully Convolutional…

Learning an empirically effective model with generalization using limited data is a challenging task for deep neural networks. In this paper, we propose a novel learning framework called PurifiedLearning to exploit task-irrelevant features…