Math and science::INF ML AI Characterizing a surface's "color" properties The reflectance of a surface determines what light leaves a surface when illuminated by a given light source. Opaque surfaces can be characterized by a spectral reflectance function. On the back side, there in a figure showing the measurement process. Can you remember what it looks like? Source James Ferwerda, Siggraph 2020

Math and science::INF ML AI Color perception A nice image of color preception

Math and science::INF ML AI Color perception A nice image of color preception Source James Ferwerda, Siggraph 2020

Math and science::INF ML AI Correlated color temperature (CCT) Correlated color temperature is a description of light source color in terms of [...] that has the same perceived color.

Math and science::INF ML AI Correlated color temperature (CCT) Correlated color temperature is a description of light source color in terms of the temperature of a blackbody radiator that has the same perceived color. Blackbody radiators are special in that their temperature is sufficient to describe an exact spectrum according to Plank's law. Source James Ferwerda, Siggraph 2020

Math and science::INF ML AI Standard illuminants Standard illuminants, defined by CIE are [what?] for which CIE has [done something]. Some examples of standard illuminants are: [natural (obsolete)] [natural] [natural][man made] [man made][man made]

Math and science::INF ML AI Standard illuminants Standard illuminants, defined by CIE are common physical illuminants for which CIE has recorded their spectral emission curves. Some examples of standard illuminants are: C D50 D65A F2L Source James Ferwerda, Siggraph 2020

\( \newcommand{\cat}[1] {\mathrm{#1}} \newcommand{\catobj}[1] {\operatorname{Obj}(\mathrm{#1})} \newcommand{\cathom}[1] {\operatorname{Hom}_{\cat{#1}}} \newcommand{\multiBetaReduction}[0] {\twoheadrightarrow_{\beta}} \newcommand{\betaReduction}[0] {\rightarrow_{\beta}} \newcommand{\betaEq}[0] {=_{\beta}} \newcommand{\string}[1] {\texttt{"}\mathtt{#1}\texttt{"}} \newcommand{\symbolq}[1] {\texttt{`}\mathtt{#1}\texttt{'}} \newcommand{\groupMul}[1] { \cdot_{\small{#1}}} \newcommand{\groupAdd}[1] { +_{\small{#1}}} \newcommand{\inv}[1] {#1^{-1} } \newcommand{\bm}[1] { \boldsymbol{#1} } \require{physics} \require{ams} \require{mathtools} \) Math and science::INF ML AI Accuracy, precision, recall [\[ \begin{aligned} \text{accuracy} &= \frac{?}{?} \\ \text{precision} &= \frac{?}{?} \\ \text{recall} &= \frac{?}{?} \\ \end{aligned} \] ] Formulated in words accuracy = [\( \frac{ \text{something} }{ \text{something} } \) ] Read more...

\( \newcommand{\cat}[1] {\mathrm{#1}} \newcommand{\catobj}[1] {\operatorname{Obj}(\mathrm{#1})} \newcommand{\cathom}[1] {\operatorname{Hom}_{\cat{#1}}} \newcommand{\multiBetaReduction}[0] {\twoheadrightarrow_{\beta}} \newcommand{\betaReduction}[0] {\rightarrow_{\beta}} \newcommand{\betaEq}[0] {=_{\beta}} \newcommand{\string}[1] {\texttt{"}\mathtt{#1}\texttt{"}} \newcommand{\symbolq}[1] {\texttt{`}\mathtt{#1}\texttt{'}} \newcommand{\groupMul}[1] { \cdot_{\small{#1}}} \newcommand{\groupAdd}[1] { +_{\small{#1}}} \newcommand{\inv}[1] {#1^{-1} } \newcommand{\bm}[1] { \boldsymbol{#1} } \require{physics} \require{ams} \require{mathtools} \) Math and science::INF ML AI Accuracy, precision, recall \[ \begin{aligned} \text{accuracy} &= \frac{TP + TN}{TP + TN + FP + FN} \\ \text{precision} &= \frac{TP}{TP + FP} \\ \text{recall} &= \frac{TP}{TP + FN} \\ \end{aligned} \] Formulated in words accuracy = \( \frac{ \text{correct} }{ \text{incorrect} } \) Read more...

\( \newcommand{\cat}[1] {\mathrm{#1}} \newcommand{\catobj}[1] {\operatorname{Obj}(\mathrm{#1})} \newcommand{\cathom}[1] {\operatorname{Hom}_{\cat{#1}}} \newcommand{\multiBetaReduction}[0] {\twoheadrightarrow_{\beta}} \newcommand{\betaReduction}[0] {\rightarrow_{\beta}} \newcommand{\betaEq}[0] {=_{\beta}} \newcommand{\string}[1] {\texttt{"}\mathtt{#1}\texttt{"}} \newcommand{\symbolq}[1] {\texttt{`}\mathtt{#1}\texttt{'}} \newcommand{\groupMul}[1] { \cdot_{\small{#1}}} \newcommand{\groupAdd}[1] { +_{\small{#1}}} \newcommand{\inv}[1] {#1^{-1} } \newcommand{\bm}[1] { \boldsymbol{#1} } \require{physics} \require{ams} \require{mathtools} \) Math and science::INF ML AI Auto-encoder (VAE?) [stub] In Karol Gregor's talk [6], e is described as [...] that limits the information passed between the encoder and decoder layers (otherwise μ,Σ, being made up of real numbers, would carry an infinite number of bits). Read more...