#eigenspectrum — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #eigenspectrum, aggregated by home.social.
-
6/10) We find that activations across different layers have an #eigenspectrum that follows a #powerlaw. Furthermore, well-defined intervals exist for the power law decay coefficient, α, where models exhibit excellent #OoD #generalization! 📈🎉🥳
-
6/10) We find that activations across different layers have an #eigenspectrum that follows a #powerlaw. Furthermore, well-defined intervals exist for the power law decay coefficient, α, where models exhibit excellent #OoD #generalization! 📈🎉🥳
-
6/10) We find that activations across different layers have an #eigenspectrum that follows a #powerlaw. Furthermore, well-defined intervals exist for the power law decay coefficient, α, where models exhibit excellent #OoD #generalization! 📈🎉🥳
-
6/10) We find that activations across different layers have an #eigenspectrum that follows a #powerlaw. Furthermore, well-defined intervals exist for the power law decay coefficient, α, where models exhibit excellent #OoD #generalization! 📈🎉🥳
-
6/10) We find that activations across different layers have an #eigenspectrum that follows a #powerlaw. Furthermore, well-defined intervals exist for the power law decay coefficient, α, where models exhibit excellent #OoD #generalization! 📈🎉🥳
-
5/10) In our paper, we study the #eigenspectrum of #DNN representations trained across different loss functions, architectures, and datasets and assess the corresponding out-of-distribution (#OoD) #generalization performance.
-
5/10) In our paper, we study the #eigenspectrum of #DNN representations trained across different loss functions, architectures, and datasets and assess the corresponding out-of-distribution (#OoD) #generalization performance.
-
5/10) In our paper, we study the #eigenspectrum of #DNN representations trained across different loss functions, architectures, and datasets and assess the corresponding out-of-distribution (#OoD) #generalization performance.
-
5/10) In our paper, we study the #eigenspectrum of #DNN representations trained across different loss functions, architectures, and datasets and assess the corresponding out-of-distribution (#OoD) #generalization performance.
-
5/10) In our paper, we study the #eigenspectrum of #DNN representations trained across different loss functions, architectures, and datasets and assess the corresponding out-of-distribution (#OoD) #generalization performance.
-
3/10) Driven by recent 🧠 findings in the #visual #cortex, we propose using the slope of the #eigenspectrum decay of the representation #covariance, termed α, as a measure of representation quality for #SSL model representations.
-
3/10) Driven by recent 🧠 findings in the #visual #cortex, we propose using the slope of the #eigenspectrum decay of the representation #covariance, termed α, as a measure of representation quality for #SSL model representations.
-
3/10) Driven by recent 🧠 findings in the #visual #cortex, we propose using the slope of the #eigenspectrum decay of the representation #covariance, termed α, as a measure of representation quality for #SSL model representations.
-
3/10) Driven by recent 🧠 findings in the #visual #cortex, we propose using the slope of the #eigenspectrum decay of the representation #covariance, termed α, as a measure of representation quality for #SSL model representations.
-
3/10) Driven by recent 🧠 findings in the #visual #cortex, we propose using the slope of the #eigenspectrum decay of the representation #covariance, termed α, as a measure of representation quality for #SSL model representations.