Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI
In the last few years, Artificial Intelligence (AI) has achieved a notable momentum that, if
harnessed appropriately, may deliver the best of expectations over many application sectors …
harnessed appropriately, may deliver the best of expectations over many application sectors …
[HTML][HTML] Analyzing biological and artificial neural networks: challenges with opportunities for synergy?
Highlights•Artificial and biological neural networks can be analyzed using similar
methods.•Neural analysis has revealed similarities between the representations in artificial …
methods.•Neural analysis has revealed similarities between the representations in artificial …
React: Out-of-distribution detection with rectified activations
Abstract Out-of-distribution (OOD) detection has received much attention lately due to its
practical importance in enhancing the safe deployment of neural networks. One of the …
practical importance in enhancing the safe deployment of neural networks. One of the …
Ties-merging: Resolving interference when merging models
Transfer learning–ie, further fine-tuning a pre-trained model on a downstream task–can
confer significant advantages, including improved downstream performance, faster …
confer significant advantages, including improved downstream performance, faster …
A toy model of universality: Reverse engineering how networks learn group operations
Universality is a key hypothesis in mechanistic interpretability–that different models learn
similar features and circuits when trained on similar tasks. In this work, we study the …
similar features and circuits when trained on similar tasks. In this work, we study the …
Toward transparent ai: A survey on interpreting the inner structures of deep neural networks
The last decade of machine learning has seen drastic increases in scale and capabilities.
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …
Rapid learning or feature reuse? towards understanding the effectiveness of maml
An important research direction in machine learning has centered around developing meta-
learning algorithms to tackle few-shot learning. An especially successful algorithm has been …
learning algorithms to tackle few-shot learning. An especially successful algorithm has been …
Similarity of neural network representations revisited
Recent work has sought to understand the behavior of neural networks by comparing
representations between layers and between different trained models. We examine methods …
representations between layers and between different trained models. We examine methods …
The quantization model of neural scaling
Abstract We propose the Quantization Model of neural scaling laws, explaining both the
observed power law dropoff of loss with model and data size, and also the sudden …
observed power law dropoff of loss with model and data size, and also the sudden …
Explainability methods for graph convolutional neural networks
With the growing use of graph convolutional neural networks (GCNNs) comes the need for
explainability. In this paper, we introduce explainability methods for GCNNs. We develop the …
explainability. In this paper, we introduce explainability methods for GCNNs. We develop the …