home.social

#relu — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #relu, aggregated by home.social.

  1. RE: mathstodon.xyz/@albertcardona/

    Cool to see a concrete alternative to #ReLU #backprop models that remains both interpretable and biologically grounded:

  2. RE: mathstodon.xyz/@albertcardona/

    Cool to see a concrete alternative to #ReLU #backprop models that remains both interpretable and biologically grounded:

  3. RE: mathstodon.xyz/@albertcardona/

    Cool to see a concrete alternative to #ReLU #backprop models that remains both interpretable and biologically grounded:

  4. RE: mathstodon.xyz/@albertcardona/

    Cool to see a concrete alternative to #ReLU #backprop models that remains both interpretable and biologically grounded:

  5. RE: mathstodon.xyz/@albertcardona/

    Cool to see a concrete alternative to #ReLU #backprop models that remains both interpretable and biologically grounded:

  6. 'Random Feature Amplification: Feature Learning and Generalization in Neural Networks', by Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett.

    jmlr.org/papers/v24/22-1132.ht

    #classifiers #neurons #relu

  7. 'Random Feature Amplification: Feature Learning and Generalization in Neural Networks', by Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett.

    jmlr.org/papers/v24/22-1132.ht

    #classifiers #neurons #relu

  8. 'Random Feature Amplification: Feature Learning and Generalization in Neural Networks', by Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett.

    jmlr.org/papers/v24/22-1132.ht

    #classifiers #neurons #relu

  9. 'Random Feature Amplification: Feature Learning and Generalization in Neural Networks', by Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett.

    jmlr.org/papers/v24/22-1132.ht

    #classifiers #neurons #relu

  10. 'Random Feature Amplification: Feature Learning and Generalization in Neural Networks', by Spencer Frei, Niladri S. Chatterji, Peter L. Bartlett.

    jmlr.org/papers/v24/22-1132.ht

    #classifiers #neurons #relu

  11. "GELU Activation Function in Deep Learning: A Comprehensive Mathematical Analysis and Performance"

    "Our findings reinforce the exceptional performance of the GELU activation function, which attains the highest test accuracy and lowest test loss among the activation functions investigated. Other activation functions, such as Hardswish and ReLU6, exhibit commendable performance as well..."

    #GELU #ReLU #HardShrink #leakyReLU #ReLU6

    🔗arxiv.org/pdf/2305.12073v1.pdf

  12. "GELU Activation Function in Deep Learning: A Comprehensive Mathematical Analysis and Performance"

    "Our findings reinforce the exceptional performance of the GELU activation function, which attains the highest test accuracy and lowest test loss among the activation functions investigated. Other activation functions, such as Hardswish and ReLU6, exhibit commendable performance as well..."

    #GELU #ReLU #HardShrink #leakyReLU #ReLU6

    🔗arxiv.org/pdf/2305.12073v1.pdf

  13. "GELU Activation Function in Deep Learning: A Comprehensive Mathematical Analysis and Performance"

    "Our findings reinforce the exceptional performance of the GELU activation function, which attains the highest test accuracy and lowest test loss among the activation functions investigated. Other activation functions, such as Hardswish and ReLU6, exhibit commendable performance as well..."

    #GELU #ReLU #HardShrink #leakyReLU #ReLU6

    🔗arxiv.org/pdf/2305.12073v1.pdf

  14. "GELU Activation Function in Deep Learning: A Comprehensive Mathematical Analysis and Performance"

    "Our findings reinforce the exceptional performance of the GELU activation function, which attains the highest test accuracy and lowest test loss among the activation functions investigated. Other activation functions, such as Hardswish and ReLU6, exhibit commendable performance as well..."

    #GELU #ReLU #HardShrink #leakyReLU #ReLU6

    🔗arxiv.org/pdf/2305.12073v1.pdf

  15. "GELU Activation Function in Deep Learning: A Comprehensive Mathematical Analysis and Performance"

    "Our findings reinforce the exceptional performance of the GELU activation function, which attains the highest test accuracy and lowest test loss among the activation functions investigated. Other activation functions, such as Hardswish and ReLU6, exhibit commendable performance as well..."

    #GELU #ReLU #HardShrink #leakyReLU #ReLU6

    🔗arxiv.org/pdf/2305.12073v1.pdf