Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Beamer Example

Avatar for eqs eqs
April 08, 2021

Beamer Example

Avatar for eqs

eqs

April 08, 2021
Tweet

More Decks by eqs

Other Decks in Education

Transcript

  1. About this Beamer project ▶ This template is available for

    both Japanese and English. ▶ 日本語と英語のどっちのプレゼンでも使えます. 2/9
  2. Commands for brackets in equations ▶ \nbracket: \left( ... \right)

    lim x→∞ ( 1 + 1 x ) x = e ▶ \cbracket: \left\{ ... \right\} β 2 N ∑ n=1 { tn − w⊤ϕ(xn) } 2 ▶ \rbracket: \left[ ... \right] ▶ \abracket: \left\langle ... \right\rangle 3/9
  3. Example 1 (highlight) x2 − 6x + 2 = x2

    − 6x + 9 − 7 = (x − 3)2 − 7 6/9
  4. Example 2 (highlightcap, cbracket) When we consider a Gaussian prior

    p(w|α) = N(w|0, α−1I), maximization of the corresponding posterior p(w|t) with respect to w is equivalent to the minimization of β 2 N ∑ n=1 { tn − w⊤ϕ(xn) } 2 + α 2 w⊤w (3.55’) the minimization corresponds to (3.27) with λ = α/β. 7/9
  5. Example 2 (highlightcap, cbracket) When we consider a Gaussian prior

    p(w|α) = N(w|0, α−1I), maximization of the corresponding posterior p(w|t) with respect to w is equivalent to the minimization of β 2 N ∑ n=1 { tn − w⊤ϕ(xn) } 2 an error function + α 2 w⊤w (3.55’) the minimization corresponds to (3.27) with λ = α/β. 7/9
  6. Example 2 (highlightcap, cbracket) When we consider a Gaussian prior

    p(w|α) = N(w|0, α−1I), maximization of the corresponding posterior p(w|t) with respect to w is equivalent to the minimization of β 2 N ∑ n=1 { tn − w⊤ϕ(xn) } 2 an error function + α 2 w⊤w a quadratic regularization (3.55’) the minimization corresponds to (3.27) with λ = α/β. 7/9
  7. Example 3 (highlightcapoverlay) For the moment, the noise precision β

    as a known constant. Where the likelihood function of t is defined as: p(t|w) = N ∏ n=1 N(tn|w⊤ϕ(xn), β−1) (3.10’) 8/9
  8. Example 3 (highlightcapoverlay) For the moment, the noise precision β

    as a known constant. Where the likelihood function of t is defined as: p(t|w) = N ∏ n=1 N(tn|w⊤ϕ(xn), β−1) The exponential of a quadratic func. of w (3.10’) 8/9