From 94aff786ff7878489516ac2f8b162c6b1a202b35 Mon Sep 17 00:00:00 2001 From: GitHub Actions Date: Tue, 23 Jul 2024 09:09:27 +0000 Subject: [PATCH] site deploy Auto-generated via {sandpaper} Source : 869e6e4df4db68dff7da85b2da5ce5046aa2ca8d Branch : md-outputs Author : GitHub Actions Time : 2024-07-23 09:09:08 +0000 Message : markdown source builds Auto-generated via {sandpaper} Source : 184fd481066598219d855d05664427bdb9fb514d Branch : main Author : Carsten Schnober Time : 2024-07-23 09:07:59 +0000 Message : Merge pull request #509 from carpentries-incubator/explain-network-figures-episode-1 Improve explanation of images in episode 1 --- 1-introduction.html | 42 +++++++-- 2-keras.html | 10 +-- 3-monitor-the-model.html | 16 ++-- 4-advanced-layer-types.html | 18 ++-- 5-transfer-learning.html | 4 +- 6-outlook.html | 2 +- aio.html | 95 +++++++++++++------- images.html | 21 ++++- instructor/1-introduction.html | 42 +++++++-- instructor/2-keras.html | 16 ++-- instructor/3-monitor-the-model.html | 22 ++--- instructor/4-advanced-layer-types.html | 28 +++--- instructor/5-transfer-learning.html | 4 +- instructor/6-outlook.html | 4 +- instructor/aio.html | 119 +++++++++++++++---------- instructor/images.html | 21 ++++- instructor/index.html | 4 +- md5sum.txt | 2 +- pkgdown.yml | 2 +- 19 files changed, 304 insertions(+), 168 deletions(-) diff --git a/1-introduction.html b/1-introduction.html index 1f9868e9..0404c015 100644 --- a/1-introduction.html +++ b/1-introduction.html @@ -527,8 +527,22 @@

1. Calculate the output for one neu

2. (optional) Calculate outputs for a network

-

Have a look at the following network:

-
A diagram of a neural network with 2 inputs, 2 hidden layer neurons, and 1 output.
  1. Calculate the output of the network for the following combinations +

    Have a look at the following network where:

    +
    • +\(X_1\) and \(X_2\) denote the two inputs of the +network.
      • +
    • +\(h_1\) and \(h_2\) denote the two neurons in the hidden +layer. They both have ReLU activation functions.
      • +
    • +\(h_1\) and \(h_2\) denotes the output neuron. It has a +ReLU activation function.
      • +
    • The value on the arrows represent the weight associated to that +input to the neuron.
      • +
    • +\(b_i\) denotes the bias term of +that specific neuron A diagram of a neural network with 2 inputs, 2 hidden layer neurons, and 1 output.
      • +
    1. Calculate the output of the network for the following combinations of inputs:
    @@ -623,16 +637,26 @@
    What makes deep learning deep le

    While traditional “shallow” networks might have had between three and five layers, deep networks often have tens or even hundreds of layers. This leads to them having millions of individual weights. The image -below shows a diagram of all the layers (there are too many neurons to -draw them all) on a deep learning network designed to detect pedestrians -in images. The input (left most) layer of the network is an image and -the final (right most) layer of the network outputs a zero or one to -determine if the input data belongs to the class of data we are -interested in. This image is from the paper “An Efficient Pedestrian +below shows a diagram of all the layers on a deep learning network +designed to detect pedestrians in images.

    +

    This image is from the paper “An Efficient Pedestrian Detection Method Based on YOLOv2” by Zhongmin Liu, Zhicai Chen, Zhanming Li, and Wenjin Hu published in Mathematical Problems in Engineering, Volume 2018

    -
    An example of a deep neural network
    +
    An example of a deep neural network
    +A visual representation of a deep neural +network used to detect pedestrians in images. There are too +many neurons to draw all of them, so each layer is represented by a +panel, with values indicating how many neurons are in each dimension of +the layer. Note that this model has 3-dimensional layers instead of the +1-dimensional layers that we introduced before. The input (left most) +layer of the network is an image of 448 x 448 pixels and 3 RGB channels. +The final (right most) layer of the network outputs a zero or one to +determine if the input data belongs to the class of data we are +interested in. The output of the previous layer is the input to the next +layer. Note that the color coding refers to different layer types that +will be introduced one by one as we proceed in this lesson.
    +
    diff --git a/2-keras.html b/2-keras.html index b0db8b22..c92bf65c 100644 --- a/2-keras.html +++ b/2-keras.html @@ -585,7 +585,7 @@

    Pairplot

    x1 x2
    x1 x2