Become a member
Sign in
Shannon entropy in the context of machine learning and AI
1K
8
Frank Preiswerk
Тхе Ань Ле
Тхе Ань Ле
Sep 6, 2018 · 1 min read

Thank you for your great explanation! Could you explain for me why in the fig. 2, self-information of direct delta function at the non-zero points is 0? According to the formula: I(p(x)) = — log(p(x)) = — log(0), should it be +∞?

    Тхе Ань Ле

    Written by

    Тхе Ань Ле

    See responses (1)

    Discover Medium

    Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch

    Make Medium yours

    Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore

    Become a member

    Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade
    AboutHelpLegal