From d2619bac0fa4d8580956a77f20ec496cb701b66f Mon Sep 17 00:00:00 2001 From: Olivier Laurent Date: Tue, 10 Sep 2024 18:31:06 +0200 Subject: [PATCH] :sparkles: Add ELSA --- assets/elsa_logo.png | Bin 0 -> 17330 bytes index.html | 39 +++++++++++++++++++++++++++++---------- 2 files changed, 29 insertions(+), 10 deletions(-) create mode 100644 assets/elsa_logo.png diff --git a/assets/elsa_logo.png b/assets/elsa_logo.png new file mode 100644 index 0000000000000000000000000000000000000000..4047d8864df45eb1a274b15a07f4dcd7ed37cc8c GIT binary patch literal 17330 zcmagFWmr_-8#YRJh*E-pk^<5xDbg)5Lk$hmFo1MR2}q|PARR;J00IL@ccXNdbobf# z`@iSC&ZqN%i@Aoi*M920pL;!f6ZSzx79WQK2MGxYUtUg19SI5f4e;{>3j_EDr&B%$ z2}#mJUP?mK{m)*yTMB4$vdeFCD7}5;IzCI2`A+YGURzaOUA%ydT!XD5$BqJiGqIvElkq?z0tFg zrlN!A#?SFWhUkmwD}-T4vD#&H%T@op;-xPMA{AjF0VD%eu ze!|XXL1RP}K$S)I5qTeyXlHRB+wXq7ZY)yaoY8MgtSc16MOT;IW6k7rW%bWTVvhh zPL`@wEJ$4_WGkO{I$oK*%VZG~Iph2MTk#vO6Ke105uaDKzt18o@GvC3bU=6hs{y+K zK1dwj3OD_^Y#Me_I=>69yM*KJ9{!wK?0&SoCKOaF0DTK3{ebgI@_KKn#;P1TIM?}? z-%>H{OW*%i@L?qvLu;MUCCdeMhEE+~4Xz6(1AlJpfQ@GNGGw$d0<-wcKxj&x>zY)! z#9l#v`Q33h2esR7>5{qN2Scuv#a|yS(km&}_qTycoEalEhg%D-Bc|aW7ibyxDR7JH zdH$`aGn>RsVX6{(^7`~=OjwisQln|+=H;DXK}k*Hd?^dvo4~e_r`ZZfUMK=cOvtD& zb4zMcqp9v`Pog1R867P0^g{PK|2ERtH#A(rgXCXJy;O@S+#C^|hTb_2^Vqb{CXi0M z{^9wT;jW%yB)9tm42V6*0qgmk8`I-9=sd|h)+18{E)V}U;s;M+E#)At;Od-V3!Qu~ zxR&k8L_TtjcbDc1>MU-XnFpD3lCPM7a0U?R4{12W3_m@)A`91wO-Y@1B+6agKg>VI zkXKd{+lZLGKtcNK{q;rhMs5+anD6cTbMm?{GunZxY6_s>L}%}IQC~#DKzz^TNa=ST z^Epk^6tj9^D4!XZ`dt_F80T2f(-~a1+zsL%hM(>a1|$tP!gG>2fm*?Ns=wO+7y~R(oln!(uMJw;Ip7WUTJUZ^d z1Lmwy1trrzhB?bZ2SgVT0WHFzL-Hh>hPEdVYrSYrC~7Lt`+DIl-C0D|Xp@wkaL-n1eMkH3n#2I7b`$lv{9&fpqP_?@eWU5&Ks+H@nOV zQ*JkId;o$Q>u)2#dl=BeTx!tbxEQt{~HvB@-BZ?_l*(r+>D6l{)60PMxwRuxFd=zqra=1e*7RYnN9 zE+(E1I~JKdLaK))fVJ3-s_en=ZBW8R*-ATIlJhcAKTsGN$*jeX)}D&MipBS1j`L_s zr6jU5I=ahO8coT#oXhLCL7LNa|KgUl8v{bFpxM7&g#4JuWBI$3tJctrt8=s>i1RVW)H-LF z8^{7E@&2F9vNL>Sn)|zfkTk?E{%~_F)p>-Gq)HeIwh|(b#T#pj5`A(w_5NuxO>Rh#ZA6!@SR2yi+Qaw<$wHhF?Zng-b>^Eyp1UoF%noZSrUPSnqMbqo@Ak_L%1yDqeUM66@X|J3%Uw| zWKtOG_2JK$$4+pZlYF>b#C&~T%q8(iP;cvt&oS7$Yo~SyKY(>R--b5Jae6U(5iFWH zK4SFMrW7bjIMn9R&W1D6`H#Qtf3mNr+P&E zw)xfdbN4@o#bMS+`+|e!TepVB5>%McKB2IUHyefW4x3Hbdkb~E^|nAx}&{>wfut#AJ^#P<@Je%I?$ z0mUQd*~EaDIdQc>%bY)6E>BipluyJNW4{m0`yTmZ>zK9qG+X|o5$1o*f* zjh3uGf)ckIWPDr9o@n;~6F>hChzxR7Ka@7iu#b(zk8Mj5I05ec| zrz?QD)mjFxAO6)Q0}G*+=D`~XcFO3xZ1^LCm2MVakW8W?4ad0MuJOc%tadssD`UmKs&Qq!@$8EDCT~Q zmLk~4e-&s$m?&X@C~_IlWf%6uW}=G8R+TTs{znMRKu$p7fw>xdbo5*keZOSP%V%GU*`H*@fA>?vOHSi z*ugsZpSSj)v$oDcpuWnP#1ah!IUSXd3A%OR^Z^(G7JNd6^>v>;q(y(;@lmuEH16Alxcxo(%X6&n{NMi1 zK+MobkhZ;(06GDn(O#xBe+3Gx_wx=0-5bfF-eRO_1y-b?jplnl(0A`87(~EaZbtnHK1^^!UZ|LsB#j772h@}=`L5D7!4Vs3pz@1ZW{#QAD(6fnh zv@TToXJ;??eMz*2^#{KDEYv9d3&*AuN%}+6Q$cEgpWi}R$*3y7pL{Gal4|&0I2ARi zD{!IgP$Cx4cclp))Am`&TMO**uCiA;PpYhBW3dND_6y4|3d;t?n!2%I7CGdX-22*t zUX4p0uN+!tLx&%X!{vKMvapWiO80;U+Jl3RDBJe@prM6Og!L;6g$#A^8$|$lIYGfZ zK!GU}hrGxky%egL!Rn8}7IqXx_WJf3@2w2gp=(O;@5Cc8}VCH;`>;L)qe=q#E$N#~*X7+uM;Jk#P3?c#Lo`_u*l~ z;RLD0JGVd8(Z@lX*LH;Y;|vqBq}s5Vxzp$>F;!haV^4J=W4|}q z-0ayQ$V9|1l~alfhn^dUl?KFJX-Xe=TW2 zAIS3xwQI?CvlbXrsQHjWq~pU(*n`vD!Q_uP34EH9_jNS`iC_q|D!d|7Zuez#S}dsB zC`E49Y?$y5!>0tx08YgKTq$tiiKUoKu1nq~W^-f)1p}-jz+n?xr&E5n39+mnP$LCi z4QM(JDp|=rGhg~NOo$^KTp z47r_cUIZn9)8tuWgE{G{u0`hEx@jp-QSC8?1jeqBboSD_%Nqrt7G-lCDU_FdM*K_b zMc-#T#}s(!227UbsNaDd$F99qnM$dpz(kC_qJK5V6e4s6drhkz-Q|@8TcBj_zcM4q z@>69jrIrIbUQ~?Bu@a*GWn(CPrYETzhS&b4ZC%GF^7gBaxukCWcn8W6SJkxvAstN6 z>Mn*L$||g+3;AKXqlZOB*R8f|Ou_6W%>TBh+8XBN&cpsB^CFjo4t8M4eWs}tgC`VJ zV`6qjWyC0Y;SPb#bp*wNz_~6uVw+ZZv6E<&=NEFjoJ2}qag*9~u&H=(dk+iiSYw!o zGCN`M zlyVR7p0uuohwq1k$Y2*TOtf@CQwTCsw2OZp$K6N2(nyUg7VBhWf*DQT4Iu9JvYu|H$du z1kC!2hZKcRJ^fW3H>zLbgL%%kL}4UBHW7S1o`wdnN{e_%fz#z9FeLBer-Biv@9Mxy zx=UT>v@jVtRwM)4HZ3w_va?TBfFwC39`i(o{ zmi&_S64C(#k|&N;uyHYMFfLepBFKw8c5;5tN{7$biceNoaUDZ!ax(4XBUkLH5;HF~ z;^j^4rzRiH?WN%Rh>vwD>99s+xNuXTrs8rK-Mny8StZt0rKrK78IsJIJjZ zv7s~-IB;~b>f)ic>WR@OV>Vu@p{&U0ojETD^HFG>foxaE1)$@2>Be)+16 ztV6RipIrgWP^HWMW0%qG0^@ebx5W$-TZ9&NfC3cbZUeqsvAAKyvuUa9QdT>+-8x?C z*T=U@)%uYD(`@!nQW)(n-;Ao2!cP)QTCi?;qPzU~pqOR45~}YxAd|zYp1vcCJ;k9< zlTwxUGega4v8PG4(rC+m`VW=g5oy`4M^Y>3W}e>~LCa`l@I5*Bt9D+rADey5M7pKn z6dis8J|m*yUI^FcvUQ`4o0Uk}JNH#kY)Pm?b7Bfp~Jyz=Sn5?7OyO zRVg5QY}U+?oStH$u|{;V7=bZvAi+B;GkD(l1+gFst2>3Hsa?^88vBEucRx2V^Ww^5 z6N$iS719c)>71a-+JdAaP{We=k^g}UxQ@U ztC2I|_^<$QS=wpZ-fCEcZJ03JWj-z7-h;mUq1WWLlnA^TH>nj_^0me!moL**ft^H0 z|BJ9+vZ~pcA*6cRVO8j!+}MRy$BxI*jJ}j|>s!Djzs0Zao*kaGX^*K*f17|{pXk@t2n0)-L#Q8+?1Kd123ee`oN!!W4E5TZtsmGEF6?- z$&4pgkCXNfWE3E%xs9Isx$H8!wHY+GB<>RN@FpYGB~19W`aDrBq5w*j-GowyT)t^S z)-1|aBG9hcX_7W|rK*eQpWpr_D*lDh$IZ13{O7ic{Qs*C{%>dhrw;x}f~MdsU4zZppx}7^|stw|Ih+CxN;0 zokl^4!d2J&6*Ltbhg3#}bfp)ulY5A6|51e2*BU^3q>B?Zlk4nJ-ch7{WsMYRDToJC z=#XqrH<4RCr!PANe)3BBjXkin5?C}2 zKw`ah-ay@}eIp%H(sAyp9b$SHX8SCRtVZI3@f^va+Mh6=qO(#= zeF8IpW`%->oMO6>2|90Q*q@f{R61yn=_`Fv=CLqp`asS;m{%KgX0epPZt3CLPm%;c z*C2m}W6PklQApAFAp%#9W2nAk)VSD$q-=4ixvB~uzYvugy$mU-*7YyLYMQ@c>etzT ziXfNcct4ZeGvxlAV{dv`4Ymu_zJImy>rl_7OhhMQtS+kA%vKn3qhO8?of zH4Cy}51>17XH6}uQ+};^p>szz9db8$PT|#i$%AnCTJy)=__@{Dhbrr!8eiq%NGoYG z5~O}%qrZ#D_MBtZnC;wSI}K)uGP(kzJg7&GRi0UNT?W&Taa1`NjysM!xqDr+JN;ivZQSPQX`{mpf1`&jP1!vlZOb!X|rzIy)oO;971 z`_tDQBwKy5V>=V`2zv=_{9F>{LU|7b-B*VWI$#c$V$l3M-G|O};uN_Hu|>+*$;bAz zQR6nhoT%zUk^H^Ik5%5rOCst0{3}0R8hKU~aD0P9_ir1ETn&ICn~pA(tdFd$f{z9TWMS#C`fp9R($y7aTnt+gXc zGsEE`G(l?eoCk62OXf0c1+SbZf-h3gMF_o1?DBG-pTFK zEL;W;9e%AapOtNu1!jGQfhP6Ue2{d8xicr;F-4IgJHU9pIKAr7G zQ!re;q51T{GjbSgWRZX1<@dPa^sDQ2DykkuyrWVb1Fz;R8xn@6?-QRA10ns{0iT=;_EC{9 z`+A9k?!Pib$A~y6sS<@}4Ub`?)ge0Gb>Pg>VH1dT-tH_z_ch}})=U23IIj7*)Uvca zE#FC2G(j@B9L}fG6{5&j$loJ(D}JI*|2+LYv#1CSm}Pb%5yO6g{T=yl*+FK6O(b!% zJ2NN#B^D=0A@M5~`DN%PreFKyQJKw(2k@|vX$$i^#*1)P?C&GhEy%aMCxNXf4*dKh z6hUGLyd_OY(QFG*08%+p>(TAf0ix@Y?{r=QVI02umm`>YN@|9MY)t@=D?E}Oe~J(S zc~atIJ}M|GNFfR>lW@d2Dnj(J7vf{PJ&Bqm55$#wc!PRG6AlX&S6k8M1!jjL}t;j zWBE~36zo&(v<#!R9^Nih*4*Ux=RllS=#36$P)N47?#4!^DMv@0Agf=FQr(i{8lFqt zR&!YSI(!vX#D;!3^|l@uDI_BNS=MmDv9!*s&k-}HI@N?XA*hAC>+gr;cY3=NY&leC z+H6S(Idq8whlve(8yAW->9a}+1^g{*b-)lq{r>D`?tI4j%O)mj?sw!epC=~ULd~m! zMnX{1L*`+^`?;PzO3~paM0f75oLo7+N_eNi(|s#MWCo2$d;ruQnf-~{qzy`NV;5TN zC`Z7shwqbe4lxusZVIKIhmA|*>pQcj&==5xP0V`WIB92fFqRxbs^Bbjin)DL%LOwc zWd8l)CE)wj3msjxekS^+)85~z#^Eqizi0{tdft{$s{!in+N{~puLS3vdtWnInv3I0 zo?U1sR>RW44NX=IBJwq;U{sc4Kg z64%sF6&I;umXA|@Z=Ya<}Y4BPGBw7*dc`iRA%T@=&P_n)BPEns0{09UfWDiAgouxBp?VSt8ZVZ*<0XgtjKS z%Z&aov`yX_{(UZV@SL^pn+dw;V zWqNH}l&}LsJcI?cbApJhYu~DWw627d!U96GNw_|W88U>>Fs|#;2dl~k5HI^KF+w(6 zn#<03lutR9#@-QNu%F#7d0Mo1eL)i|-W4g?)S+(bl0*y#4EMzeqq*B(#V7`soLv=vfb6XmrVHC1NGT0H5qPVe*@@_&3F-2f$%>qrB%&BL%#W zOXJW8f2ln6vOy2_p}>|FSsbN>I-g|VsS01!@j*mu=zSB$W!)EI z<%yQc1A-)95*yC++*ljA0T|o9(*zR4d8Yuurl>t>J zk&5hCm{CBGTz%05^vJ|>0^whLi)6+$_yg7h?Zrc%!)&&GQX3~C4tTVm(D4}~C!zTD z*E}mkTB;|Zq+ldl!St?(aBMD#N~WmhtwH(8^7O6>+-~JWDcgr9%ew0HgR{aG=wk(C+RY4=p(#v1G^Hlz&e75#hG-wDhF@wvO7sP>;xF4hN#TTmD_ z_tQ4Gd6_xx;Wrv6huAdJMfjA=r8)g!y73JxsZ_e~QEL=|;Ep0~=6m)0c~Kty@LYQ= zi0`KgxG$D=RtF%Eg87oo3W8ws_uET$?+k&al1!$VZd{UG@<2Nn;D?;yYDlT4>05r- zXJjOkFH$m_`YM;R?)noiIKE-qyjA<<{af@^tM^%pah##O2kf>%6~)rvGi3;D;Uo~9 zcC>}}`x9~^9R=E~Oo0=7Q&ancr4(j;`gIW<$D}SStAiQ!=>*)GsC?(0VpFuqNs1iO z&d+@gd}M~Wh7S_y0@vAO)%0_<%D=v42itfJMB0?UM?T;`p|0i4J>s34W_{OoY7+VT zfns#N3(Gs_)JK(KEa(sN*=t*;@SjzIW=JIoyDeQOfx&S7`}NrVQglaeTZwCLo};d@ z6b1p>Z*AE+6KYHwdI39(L69dJx%k_RRv6}mQRwx}cyzIYKft3K;*XTCHAvR<05m%eYnE|Jh_UMa>AEv%4 zUFO>LcE;$he(S_BMBExrQjbRVX+UKxm){aaP3c6sta=%i}Pt<&Pts+VFFU@wr+e|x0qCu`M0MR z;g0etYA72vl{RG)zbLRohyc7znLw6<|R+NXQj5;6tW7t$)Gdw2?kRdTky)OXMe5kB~n;P|S2 zE=uu2`vog#($M*K9Im|^3!mR&g7y|O^>DgByR@mRtd$bR{nUV_=07XSI{dPy!zxoh zqTZ}`B4QAgiqKl=n_I_T@#(nKr6R`oT!;B6O}>S4D;SyGWtq440R3uP4YFofReX*t zmXCKUL(+E=*bEF=p3at@LM6betSe)9-NG_`aXoIDsNzZLWPN9FdUimhi3}57TfX;} zT%9ZW7+rEa)MEt+pOunu-g0L!;?F<0SsA0nF>AYJI*+x3Q&~gbsyg#*c{1B$HW^}2 z?XO?8AujEkT#sPDu~&DFef_{xrq8JNuj5>o0S%-vHq)vbz!`D|&0iu>L+-#?UZ54( z5{OSDCE5$Tlq&0|#37)@nEQLx=EhLrS-JlT{v!DtiVcH4uaT8MOhy(49xnwC46;;S zqRma+^NMy$BK*>f&WPY_r>a)dbWV~Ot9AF{Fh8wjlwAkQiXC8iVo4?!+^qXPgGMUz zcUhQ#oYN(*z1D7g74fb)UkLo&J!F{BH=AwY%U`$7^+~1eYr4*t75ZE)bFINR58Tl-pTccod%Y%jDbs0EVQs85smy_d18=(BN5(WH5^F;c zcx8tPP-3O%Ua-@8ZD*&tmMUy_Mbm5ELpMmqBvERITTk;`;eqUxp4N72z$PXxC0$7e zR4@NG8irx+@-3Avc586I@it7bzY=F?vbU9rwa$l!RMS3PZTiPZ{Z0nm=>d;-k7SOsC)y4OF-ZO?+w=WHxdbS5?XT#+Gz;ag8m=_pQ~2`!86)*Pn)2)?9*YoJpSd%CMs_7tBtW}V(Sz(vX^ zp}n1k$?FYr+~lmHdmO*#G3OF9(zdSJa*kD^5>+0Q8k=Oes*X~HK~BQstBpRynwh0X z+N@&k8m6EqMfvA!I-=y&J9Spb6fzyXk*K`G24fd)8gFc47FI2nuFOJ=j>XtwOt~4q z2mwiFPHI(}Lby}Zapf#6`XG2xC+w(x=>mU%?Jm$dQ50mJx=#nv#wVv~Ull{K3%liF zG|o;I*c`9uS|_ayfA^fs!EWYrB`EVUPj5tEHX_qdtBi>|hbgzAL=!2!c93p*optbE z>#fYZCh?b)igNKbq2T3*p24?YLzJV_;V(+Xd+y-s^iRi%=i#KW-3N}dS2U9*9xeNn zAd{`~u(^zjQsA+|F85RR@%DNFd@J@?+EQd+x;yJPsDAkD$c-wmqI_vHF8LM^>FnQ< z&+ETb(2z-7)24LI9VyI>*66Jp|2i3DpE%g;%@LFmcU(1&{Fy?7Y|QOC+B$Olw72M# zgkA|`3kXF@+R*q@B%;~Y*Ll~`B|+l9=6-x~zFDOBtLY5W1djJpeJ5X2F3GvPvVv;f zfmfa3-1LKXCmhp8!@tr!{%BPCE1(A)Oj}p-NWTAA%R(spL>l40`^Pr&N$&Gx)5Pw(nQKk2UJ46@R4 zF;&b)<1f@EzCPA#LHs;9oLntE(`gD7N%P3FNNt;F`H#%8`Wiic)Ta1z z!5WA-?F}DWWK-^Zd1vD@FEY#A%COI^&BQ0x#UV4~Y@cs>(8U$n7D;zObeW}A`7N52 zYveSG6?6w_{JzqTRCe+W8@!^bBNY+kY`Mx}O)Z%dn>eO2vV4P^$XzbYug~vfHdAY_ ztUp&MaqFAd#=$!lx|#DYUq((pp=5S@c%z&l96*`Mx@56sAeV}Tr~jg9g#fPl!F}0k z$!eHzVQNLaWa-3qZeLs7ex1W|Wh?ygC50_4+xGN7;xuFv>3NwwrKe+a1JdEFY&9SA zWVElo^1&P5s||jVBzp%$9Y8h}d};T^-1&td1PYA#)8VJ_OwfQ8GH31m-y^ZFP@c7U zam6g~PE0LWRz|Z6t1!^Q7I^7-_kZoN*x3PZ7UNQQz4LK9;2@txlm9VT=3U9(ETXnj zNL|O&UQ|soHG)D#5eBpVL+CD|1e%+rI#Ux4$$@%Ujyv{_IjoFX>=SB`q&41XGc;Ak zk*rj;U39NI;^kzKXem5DWQFQ2e`I@}+Wr#q)%MHAujbN;ZeuQ=7peKt5hmB#2xCK$(Q8j?&Tew(F*3qc-;&&QEleF z4|(aCrg-?6D+g`qSlZG3A~Zq5DoMC_om5Uy?W!GSgX}*@CRLkAjC*Cp3AO&@VNHKo zw&8ZkvBn&gKY0!}<&$*O8OD&5-C7N%g}vWi)iS*%Kg*g!C({s;N2{+%&qQlbW}xlu zHl_0BAOGO=mhAXjXn$4&#X?k4CvQ?n$4DttNe$gAwZLAxT&m38L+B_`bYYm)r)Y!g zqA-0JUlVEGad1Sf350<6qi#!yQ%P$(`m06Tu3XiT50SjE3%fNT$8T9SntWg}23O+t zoNud~gFgJq`+P$F)KmwrN1N=dR|KWQ)^sBkf7zZyssH^W-RL@T)Yw3$eq_pg#!K%j zBWnmu5@T)kgv3V4r@Izv+1d^l;6anL!8Gjaf%xLCD6F4mF0`uZ7Hn7Ua7~<8N1XR< zmF%q=iFzAIXNuHkiL7~u1C%n;^sG8ZOBg@oS14oee|S)Zny0yGog-iMB~Nb(OT8G^UyoJ~{-RQ+e$%e7?1?Uh_j4@a1Bmkwi6XU@V6^X=;Lss4 z#6yg&XNJa&xCfY$--~=Bbng~#l45oLDYUi#f65<>(9fWG(@hnU&PKLo1)2PkI^%UQ zJ~J>Tm~5l|^T&lRntKz81x}8qKBipsd0y7bWk%6{NucToXBK+S6wlb>p_qoP`$_H%UNy>79ah|)AUt|&irVHC4z1Kg6Mvptrh5; z#6?lu><0>hISwT1@!Q#isSWnANPSDeP&f24)=y?4x5Vx*UCX(*ckn3w^lSA#^Z0cV z*zFIpd&R!p{wdO&jXipQ7_P3!10`Yil^u_KN5S-_`4<}cUetOZTT21U$5VbWU_G>^3cLWVH9Xu=cV|J-6Fm)!p|{vySwO>n9cB zWu^S1K71ZWW!x4_Z(v;8S5q0G`)+XTB)KP?I>|L1bAH4wf;`F+BaPC^!a{Xn0GGtG6F~) zw_*ch?Tm6FL*+Zq8W8saXqvqn1TWFN->k<$g7Nb8nzVKFM!y(&vk zR{+USlLRP_tXv9IIlPw`I|+1ZaN^0^x>zbEFZ%$Y<9-z#`{O*O_X-%@`VAj)qcWVP zITq~ZR24CBW40Dch#73`Na~0k5R`IbZcz(ZS7au6w0;NzPf9Vz7GIP` z>hSSEK}t;4-Rpk9Xg=5Jb)ILv$Mx;v+LS0wb%JNV?qyX%Sxl7j1lyCgmSEQC8$w8I zJy1P1=A!Bkeg!?dY!uc;XWeJ-Z$B^G@KnWBGrzCbPtwTxw1tiCwQEA!6V`a}u9JU% z>W-&VoIm`pADv>Q!So_7T%Yu>82rzMn{-6LTx^87G^wS@LUE@vB|d{Ulg)DKY+vQ? zDA2_~TU#U=jaVyu5k)RRt|cOtDm+|z&cg8uOK zs-SO=4e1fG56Sr#&Aj*3xj7`^Or_zSqWw~bnV=81)u~Jl^&i-q&A#9z#X35?`Ffga z=8Cz`d4mT)y+4UKo}$EqqC(aYB)ocWgJlcgbXq-y#xn7zT>eK>;U{T)R=$~}2Y)uM z+EA-zTFO9smH=fXM(Vt-x=e3zO9Kb=Ucc4rJK`?$>RznP&QIG~=l1flS#QZ81izfm zBG)Tgd2PCW?gP%{S3ylna59Ltv7u@0B5k&*slAnAdT}+AALilU>6E>R`HXJ}oB1}G zBJ33yz)U@4K8+W7V~K^vjE5hWHll$DeJ($B)0v@vxhjr_2+UU2`THU#^*pw7>8kBy zEVEE>O>M0Ib)A4FsrQ8bCB@RBl~A2VZD)D%nUhh(U0XOOLDW$&Hc@sZM5&16JZq}_{;D$Q9^MNZR3>&3%N z*uUtV&VA;VZ-phb?AvxJcq&{QE+~u@1Lw)ss=8KIpE=1cgy#0Dk&fVMUi8BkIZdbC zyv>ZVgY%U;E7=^Aheh=ZKIZhuwR<(THDw>MRJvz;;?>H>FP>MgC7Y$tOyaZ*kNT*@ zGt`Nukv%8Z@TVHYQ)=GCq%>*5`Id4)mAa3Z+rU6pOLu4>cChlgE~qs6`&K<=G`#ao z5{Fn!h{iq7Sv-EY)t2})6KRLG;`BSYjXIsMnPP}se`8-ljPz$m+kz|pJxJpC2j^z7 zJ)Nq`nd0h^EW*Z_46;r_QKHGlH>8m+V|T}{Bi#Z40*OvXJlm`HRYD)FkuSe9p6FE? zT{4kGQ_*`&=QsP+IrY~Zo=0sTh3b+=_p!7=Hkor)icYF9&ScDvTDF(Tql!3IX zk?+k0c;DC!@x?=L6ri=d3)d7*AGXyv8UsV`{ro!%BYhAM_7ia z-O`y6r-ZO4JMRXO6vUwWBYHMq-TM6S%ZlxZ+1@^*&zr=#p%HISlzO$=xQl|u8fkmu zzq+%IO|uSWSMx4xhrS`by5U&+-p>iX$<@5xX!h2oZXepf+68syT%(!-6RO&$_j-mHIfeAj` z7ZZN@5xt(&1zx&lnQT{ya9N7_Sv%$K1CXK1zNO4Yp)d z_&(GX`J&KKh@{@;7UB%M$#KH;T8%r!Fn9kEgz;c`w^O7&Qmygh-P$NHE6k9734iAp zXo<-FSkBSY_+{wr-mFxb?eIyUaRv=>Ug`ITq`ahG=nt~|M?bxQoEqLzR3WKz1*gx< z@N5Zp*G-0x^R&KvPQ3E;T88gvA=p}C;VGHf6MVaYjCK+UCB=>JhK1xR65XC%BDg=Z z4F{0VZC3PM$Iawx-qYZUhzkM}c`mkzZVC$5&X8W4Fn-Iae2yO(;^KX#Hl=erB>j3Y zE}>*bei0FIIZt0sc<`zrBP;WtZ=%o0DjfDVReDXyAO$C8&cJ(Cb9E-aVlu~&h<`EK zIiOcKBs0{Z*Yl|V?(G_X4T&1@LCA`V&nWvkHzICUoP1R#%NN4GAr4mRw%z)8TXE}M zW`$D`o|`RIDbcI{P%ykO^D57Fdd-&fzgS;lrj;>$2y<-)z9>6S}0fzxnyBzl;&F_vveFr`jv=2Vmx45Z$0@ zem$3UJ@*kZG?d15v1O5}xyizRsP}DGQAB)(R(*jic~gVE-JSkpo?UYGep%bY7qbiC zkv=QKt*B$s6S~}(yD>*XHs|HX`GUKh0T5F$JMLj+isLpk@0$nO%qI!-PA; z`53h7=D{!h?1aDR@*5#B>@p^QG_mxqQ4qPHB0Eo%O(7o6t-F7t3jV2AtlVY<VSH`~LoZ~wzBE#zDKIOFUPSYy8V^<&Yzm;Qb7sg) z*M04^tPa}mO3!@b&~e$CkGNy1F^bH3WycgnVV8QF@|Pb%kmyFbqVnub?^FuVxN8-_ z_Z6h$&Nc4k!)scS>nJ~ui(pb%FqhSZ>!R?6cW#!)en!&>)=XW-cqrw*d)uleyXCFB z($$0k?+bKYjN8aQ^uh9#MBL)$-V0QmLbUk3- z=+&xdHwDsW^UVSJ>9B)|7cC$CVej{6D-CKVcg|{9)OL<1r1^3;N9p+CSt2ffp6Iv?@U~$NMTBmo@?wh0gD$vRV@#jS4+c53Ogeb6 zy(&qYGssKt%4o{IXrkOc8zBC(+$l7EHVr;-_9036n^^@o_mW}z7I`f3qIa-&)jwAE zmjM6yMaqz!rr^rtjLB2J(=YrOzCRjT-b9oQVzbSx@(vl|YLF=E663zfye=b+5cAAu mDuNukrizuI`93`G{6A~zeHHsDYbo$74hBzGKbLh*2~7a4P!lBp literal 0 HcmV?d00001 diff --git a/index.html b/index.html index e839672..3685aa0 100755 --- a/index.html +++ b/index.html @@ -97,19 +97,22 @@

Outline

Introduction: Why & where is UQ helpful?

Initial exploration into the critical role of uncertainty quantification (UQ) within the realm - of computer vision (CV): participants will gain an understanding of why it’s essential to consider uncertainty in CV, especially concerning decision-making in complex + of computer vision (CV): participants will gain an understanding of why it’s essential to consider + uncertainty in CV, especially concerning decision-making in complex environments. We will introduce real-world scenarios where uncertainty can profoundly impact model performance and safety, setting the stage for deeper exploration through out the tutorial.

From maximum a posteriori to BNNs.

In this part, we will journey through the evolution of UQ techniques, starting - from classic approaches such as maximum a posteriori estimation to the more ellaborate Bayesian Neural Networks. The participants will grasp the conceptual foundations + from classic approaches such as maximum a posteriori estimation to the more ellaborate Bayesian Neural + Networks. The participants will grasp the conceptual foundations of UQ, laying the groundwork for the subsequent discussions of Bayesian methods.

Strategies for BNN posterior inference.

- This is the core part, which will dive into the process of estimating the posterior distribution of BNNs. The participants + This is the core part, which will dive into the process of estimating the posterior distribution of BNNs. + The participants will gain insights into the computational complexities involved in modeling uncertainty through a comprehensive overview of techniques such as Variational Inference (VI), Hamiltonian Monte Carlo (HMC), and Langevin Dynamics. Moreover, we will explore @@ -118,19 +121,21 @@

Strategies for BNN posterior inference.

Computationally-efficient BNNs for CV.

- Here, we will present recent techniques to improve the computational efficiency of BNNs for computer vision tasks. + Here, we will present recent techniques to improve the computational efficiency of BNNs for computer vision + tasks. We will present different forms of obtaining BNNs from a intermediate checkpoints, weight trajectories during a training run, different types of variational subnetworks, etc., along with their main strenghts and limitations.

Convert your DNN into a BNN: post-hoc BNN inference.

-

- This segment focuses on post-hoc inference techniques, with a focus on Laplace approximation. The participants +

+ This segment focuses on post-hoc inference techniques, with a focus on Laplace approximation. The + participants will learn how Laplace approximation serves as a computationally efficient method for approximating the posterior distribution of Bayesian Neural Networks.

Quality of estimated uncertainty and practical examples.

-

+

In the final session, participants will learn how to evaluate the quality of UQ in practi- cal settings. We will develop multiple approaches to assess the reliability and calibra- tion of uncertainty estimates, equipping participants with the tools to gauge the robust- @@ -142,9 +147,10 @@

Quality of estimated uncertainty and practical exam

Uncertainty Quantification Framework.

-

- This tutorial will also very quickly introduce the TorchUncertainty - library, an uncertainty-aware open-source framework for training models in PyTorch. +

+ This tutorial will also very quickly introduce the TorchUncertainty + library, an uncertainty-aware open-source framework for training models in PyTorch.

@@ -202,8 +208,21 @@

Selected References

href="https://github.com/ensta-u2is-ai/awesome-uncertainty-deeplearning">Awesome Uncertainty in deep learning. + +
+ +
+

Andrei Bursuc is supported by

+ +
+ +
+ +
+ +