Update bigmax tutorial

conv-nn-bigmax-2019/bigmax_mnist_example_tutorial.html

@@ -11775,7 +11775,7 @@ div#notebook {
 </div>
 <div class="inner_cell">
 <div class="text_cell_render border-box-sizing rendered_html">
-<h1 id="(Convolutional)-Neural-network-tutorial---BigMax-workshop---Dresden,-April-2019">(Convolutional) Neural network tutorial - BigMax workshop - Dresden, April 2019<a class="anchor-link" href="#(Convolutional)-Neural-network-tutorial---BigMax-workshop---Dresden,-April-2019">&#182;</a></h1><h5 id="Authors:-Angelo-Ziletti,-Andreas-Leitherer,-and-Luca-M.-Ghiringhelli---Fritz-Haber-Institute-of-the-Max-Planck-Society,-Berlin">Authors: Angelo Ziletti, Andreas Leitherer, and Luca M. Ghiringhelli - Fritz Haber Institute of the Max Planck Society, Berlin<a class="anchor-link" href="#Authors:-Angelo-Ziletti,-Andreas-Leitherer,-and-Luca-M.-Ghiringhelli---Fritz-Haber-Institute-of-the-Max-Planck-Society,-Berlin">&#182;</a></h5><p>In this tutorial, we briefly introduce the main ideas behind convolutional neural networks, build a neural network model, and finally explain the classification decision process using attentive response maps.</p>
+<h1 id="(Convolutional)-Neural-network-tutorial---BigMax-workshop---Dresden,-April-2019">(Convolutional) Neural network tutorial - BigMax workshop - Dresden, April 2019<a class="anchor-link" href="#(Convolutional)-Neural-network-tutorial---BigMax-workshop---Dresden,-April-2019">&#182;</a></h1><h5 id="Authors:-Angelo-Ziletti,-Andreas-Leitherer,-and-Luca-M.-Ghiringhelli---Fritz-Haber-Institute-of-the-Max-Planck-Society,-Berlin">Authors: Angelo Ziletti, Andreas Leitherer, and Luca M. Ghiringhelli - Fritz Haber Institute of the Max Planck Society, Berlin<a class="anchor-link" href="#Authors:-Angelo-Ziletti,-Andreas-Leitherer,-and-Luca-M.-Ghiringhelli---Fritz-Haber-Institute-of-the-Max-Planck-Society,-Berlin">&#182;</a></h5><p>In this tutorial, we briefly introduce the main ideas behind convolutional neural networks, build a neural network model with Keras, and explain the classification decision process using attentive response maps.</p>
 
 </div>
 </div>
@@ -11991,10 +11991,10 @@ Convolutional networks have been tremendously successful in practical applicatio
 <p>The name "convolutional neural network" indicates that the network employs a mathematical operation called convolution. Convolution is a specialized kind of linear operation.</p>
 <p>A typical layer of a convolutional network consists of three stages:</p>
 <ol>
-<li><p><strong>Convolution</strong> stage: the layer performs several convolutions in parallel to produce a set of linear activations.</p>
+<li><p><strong>Convolution</strong> stage: the layer performs several convolutions in parallel to produce a set of linear activations (see Sec. 3 for more details).</p>
 </li>
 <li><p><strong>Detector</strong> stage: each linear activation is run through a nonlinear activation function (e.g. rectified linear 
-activation function)</p>
+activation function, sigmoid or tanh function)</p>
 </li>
 <li><p><strong>Pooling</strong> stage: a pooling function is used to modify (downsample) the output of the layer. A pooling function replaces the output of the network at a certain location with a summary statistic of the nearby outputs. For example, the max pooling operation reports the maximum output within a rectangular neighborhood. Other popular pooling functions include the average of a rectangular neighborhood, the $L^2$ norm of a rectangular neighborhood, or a weighted average based on the distance from the central pixel.</p>
 </li>

conv-nn-bigmax-2019/bigmax_mnist_example_tutorial.ipynb

@@ -9,7 +9,7 @@
     "\n",
     "##### Authors: Angelo Ziletti, Andreas Leitherer, and Luca M. Ghiringhelli - Fritz Haber Institute of the Max Planck Society, Berlin\n",
     "\n",
-    "In this tutorial, we briefly introduce the main ideas behind convolutional neural networks, build a neural network model, and finally explain the classification decision process using attentive response maps."
+    "In this tutorial, we briefly introduce the main ideas behind convolutional neural networks, build a neural network model with Keras, and explain the classification decision process using attentive response maps."
    ]
   },
   {
@@ -203,10 +203,10 @@
     "\n",
     "\n",
     "A typical layer of a convolutional network consists of three stages:\n",
-    "1. **Convolution** stage: the layer performs several convolutions in parallel to produce a set of linear activations. \n",
+    "1. **Convolution** stage: the layer performs several convolutions in parallel to produce a set of linear activations (see Sec. 3 for more details).\n",
     "\n",
     "2. **Detector** stage: each linear activation is run through a nonlinear activation function (e.g. rectified linear \n",
-    "activation function)\n",
+    "activation function, sigmoid or tanh function)\n",
     "\n",
     "3. **Pooling** stage: a pooling function is used to modify (downsample) the output of the layer. A pooling function replaces the output of the network at a certain location with a summary statistic of the nearby outputs. For example, the max pooling operation reports the maximum output within a rectangular neighborhood. Other popular pooling functions include the average of a rectangular neighborhood, the $L^2$ norm of a rectangular neighborhood, or a weighted average based on the distance from the central pixel.\n",
     "\n",
@@ -357,7 +357,9 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# this can be skipped because the images are already saved on the server\n",
@@ -386,7 +388,8 @@
    "metadata": {
     "code_folding": [
      7
-    ]
+    ],
+    "collapsed": true
    },
    "outputs": [],
    "source": [
@@ -428,7 +431,9 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "# read jpg files as numpy arrays\n",
@@ -511,7 +516,9 @@
   {
    "cell_type": "code",
    "execution_count": 6,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "k_identity = np.array([[0., 0., 0.], \n",
@@ -558,7 +565,9 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "kernels = [k_identity, k_box_blur, k_vlines, k_hlines, k_edges, k_emboss]\n",
@@ -1223,7 +1232,9 @@
   {
    "cell_type": "code",
    "execution_count": 20,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "from vis.visualization import visualize_saliency\n",
@@ -1437,16 +1448,18 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": []
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python [conda env:py37]",
    "language": "python",
-   "name": "python3"
+   "name": "conda-env-py37-py"
   },
   "language_info": {
    "codemirror_mode": {