From 4db982a6985ccfa5b38204633e46d31f074b2269 Mon Sep 17 00:00:00 2001 From: Morten Hjorth-Jensen Date: Wed, 3 Nov 2021 08:00:38 +0100 Subject: [PATCH] update of typos --- doc/pub/week39/html/week39-reveal.html | 6 +- doc/pub/week39/html/week39-solarized.html | 6 +- doc/pub/week39/html/week39.html | 6 +- doc/pub/week39/ipynb/ipynb-week39-src.tar.gz | Bin 193 -> 192 bytes doc/pub/week39/ipynb/week39.ipynb | 402 ++++++++--------- doc/pub/week40/html/._week40-bs012.html | 6 +- doc/pub/week40/html/week40-reveal.html | 6 +- doc/pub/week40/html/week40-solarized.html | 6 +- doc/pub/week40/html/week40.html | 6 +- doc/pub/week40/ipynb/ipynb-week40-src.tar.gz | Bin 34326 -> 34326 bytes doc/pub/week40/ipynb/week40.ipynb | 426 +++++++++---------- doc/src/week39/week39.do.txt | 6 +- doc/src/week40/week40.do.txt | 6 +- 13 files changed, 441 insertions(+), 441 deletions(-) diff --git a/doc/pub/week39/html/week39-reveal.html b/doc/pub/week39/html/week39-reveal.html index 7271e8515..3bc363cd9 100644 --- a/doc/pub/week39/html/week39-reveal.html +++ b/doc/pub/week39/html/week39-reveal.html @@ -2246,9 +2246,9 @@ theta = np.random.randn(2,1) for epoch in range(n_epochs): # Can you figure out a better way of setting up the contributions to each batch? for i in range(m): - random_index = np.random.randint(m) - xi = X[random_index*M:random_index*M+M] - yi = y[random_index*M:random_index*M+M] + random_index = M*np.random.randint(m) + xi = X[random_index:random_index+M] + yi = y[random_index:random_index+M] gradients = (2.0/M)* xi.T @ ((xi @ theta)-yi) eta = learning_schedule(epoch*m+i) theta = theta - eta*gradients diff --git a/doc/pub/week39/html/week39-solarized.html b/doc/pub/week39/html/week39-solarized.html index 4ad4e500f..db67d2a6f 100644 --- a/doc/pub/week39/html/week39-solarized.html +++ b/doc/pub/week39/html/week39-solarized.html @@ -2133,9 +2133,9 @@ theta = np.random.randn(2,1) for epoch in range(n_epochs): # Can you figure out a better way of setting up the contributions to each batch? for i in range(m): - random_index = np.random.randint(m) - xi = X[random_index*M:random_index*M+M] - yi = y[random_index*M:random_index*M+M] + random_index = M*np.random.randint(m) + xi = X[random_index:random_index+M] + yi = y[random_index:random_index+M] gradients = (2.0/M)* xi.T @ ((xi @ theta)-yi) eta = learning_schedule(epoch*m+i) theta = theta - eta*gradients diff --git a/doc/pub/week39/html/week39.html b/doc/pub/week39/html/week39.html index 82bb8a138..7464180a5 100644 --- a/doc/pub/week39/html/week39.html +++ b/doc/pub/week39/html/week39.html @@ -2210,9 +2210,9 @@ theta = np.random.randn(2,1) for epoch in range(n_epochs): # Can you figure out a better way of setting up the contributions to each batch? for i in range(m): - random_index = np.random.randint(m) - xi = X[random_index*M:random_index*M+M] - yi = y[random_index*M:random_index*M+M] + random_index = M*np.random.randint(m) + xi = X[random_index:random_index+M] + yi = y[random_index:random_index+M] gradients = (2.0/M)* xi.T @ ((xi @ theta)-yi) eta = learning_schedule(epoch*m+i) theta = theta - eta*gradients diff --git a/doc/pub/week39/ipynb/ipynb-week39-src.tar.gz b/doc/pub/week39/ipynb/ipynb-week39-src.tar.gz index 3e20937d1a423c574899f2748602524746b72f66..d511de4b10fe0ff4a1760adf966602354dbdcf19 100644 GIT binary patch literal 192 zcmV;x06+g9iwFQ(GlF3N1MSbv3c@f92k@Qu6nTQtuHD3=;0_)H5nrHVnX9^XwjH{+ zcORf9#mf+(zssMH5R!eiT5q$+-CZynLP*Lv47o^?F-bhtBT5sXoN~e$O;`+svLq$} zkoit}X{{5cKc%its4S{?bNyIZe%Ld;0?+&the}%5>^fIz1xh>2wLZfQ@ywQyY&w-g uq0tU4FnDdHK@h3~Q54cit;8j4j6NDs+bI0?GoI&p-q#)k{Ecb=2mkZ)`M^3WlO=ml0>b2E2sccpy$ z{D3+YT_l42UH%L+3^Rvpz1d}fy<2ZFh?r0cW2Q+wC5Cf7AtVMu2}K%Vno>X##bN3J zE_c#PXDrjhDNS|e(s221ZWt@e4}0cU;F*8oSP28$eQzrzK`P60rE0iwUPr4yw7txs vP~40y(EQp7&4I}tSWyTolw=pb)#{{KV*>xz&p3|bIA41Jf6hY?00;m8= np.for epoch in range(n_epochs): # Can you figure out a better way of setting up the contributions to each batch? for i in range(m): - random_index = np.random.randint(m) - xi = X[random_index*M:random_index*M+M] - yi = y[random_index*M:random_index*M+M] + random_index = M*np.random.randint(m) + xi = X[random_index:random_index+M] + yi = y[random_index:random_index+M] gradients = (2.0/M)* xi.T @ ((xi @ theta)-yi) eta = learning_schedule(epoch*m+i) theta = theta - eta*gradients diff --git a/doc/pub/week40/html/week40-reveal.html b/doc/pub/week40/html/week40-reveal.html index 3aad4d3c1..cc773c1c2 100644 --- a/doc/pub/week40/html/week40-reveal.html +++ b/doc/pub/week40/html/week40-reveal.html @@ -547,9 +547,9 @@ theta = np.random.randn(2,for epoch in range(n_epochs): # Can you figure out a better way of setting up the contributions to each batch? for i in range(m): - random_index = np.random.randint(m) - xi = X[random_index*M:random_index*M+M] - yi = y[random_index*M:random_index*M+M] + random_index = M*np.random.randint(m) + xi = X[random_index:random_index+M] + yi = y[random_index:random_index+M] gradients = (2.0/M)* xi.T @ ((xi @ theta)-yi) eta = learning_schedule(epoch*m+i) theta = theta - eta*gradients diff --git a/doc/pub/week40/html/week40-solarized.html b/doc/pub/week40/html/week40-solarized.html index d3532d62a..9cf4831de 100644 --- a/doc/pub/week40/html/week40-solarized.html +++ b/doc/pub/week40/html/week40-solarized.html @@ -594,9 +594,9 @@ theta = np.random.randn(2,for epoch in range(n_epochs): # Can you figure out a better way of setting up the contributions to each batch? for i in range(m): - random_index = np.random.randint(m) - xi = X[random_index*M:random_index*M+M] - yi = y[random_index*M:random_index*M+M] + random_index = M*np.random.randint(m) + xi = X[random_index:random_index+M] + yi = y[random_index:random_index+M] gradients = (2.0/M)* xi.T @ ((xi @ theta)-yi) eta = learning_schedule(epoch*m+i) theta = theta - eta*gradients diff --git a/doc/pub/week40/html/week40.html b/doc/pub/week40/html/week40.html index da6c5d4ee..952eee87b 100644 --- a/doc/pub/week40/html/week40.html +++ b/doc/pub/week40/html/week40.html @@ -671,9 +671,9 @@ theta = np.for epoch in range(n_epochs): # Can you figure out a better way of setting up the contributions to each batch? for i in range(m): - random_index = np.random.randint(m) - xi = X[random_index*M:random_index*M+M] - yi = y[random_index*M:random_index*M+M] + random_index = M*np.random.randint(m) + xi = X[random_index:random_index+M] + yi = y[random_index:random_index+M] gradients = (2.0/M)* xi.T @ ((xi @ theta)-yi) eta = learning_schedule(epoch*m+i) theta = theta - eta*gradients diff --git a/doc/pub/week40/ipynb/ipynb-week40-src.tar.gz b/doc/pub/week40/ipynb/ipynb-week40-src.tar.gz index 7878018fcac7c2541dd22ae2fef9259cdba8d82e..61f42d6a114078c669bf0ea2ad972fbd5131f760 100644 GIT binary patch delta 17 YcmbQ%!!)gjiA}zngQ3fKBbz`Q05G2g3jhEB delta 17 YcmbQ%!!)gjiA}zngTdKwBbz`Q050nU!T