Search Results for author:
Found 5 papers, 2 papers with code
Causal Concept Embedding Models: Beyond Causal Opacity in Deep Learning
Causal opacity denotes the difficulty in understanding the "hidden" causal structure underlying a deep neural network's (DNN) reasoning.
AnyCBMs: How to Turn Any Black Box into a Concept Bottleneck Model
Interpretable deep learning aims at developing neural architectures whose decision-making processes could be understood by their users.
Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning
Federated Learning (FL), a privacy-aware approach in distributed deep learning environments, enables many clients to collaboratively train a model without sharing sensitive data, thereby reducing privacy risks.
Climbing the Ladder of Interpretability with Counterfactual Concept Bottleneck Models
"), and imagine alternative scenarios that could result in different predictions (the "What if?").
SHARCS: Shared Concept Space for Explainable Multimodal Learning
Multimodal learning is an essential paradigm for addressing complex real-world problems, where individual data modalities are typically insufficient to accurately solve a given modelling task.
