+ backpropagation edits

Mark-Kramer · Oct 3, 2024 · b8eb222 · b8eb222
1 parent 5c1afef
commit b8eb222
Show file tree

Hide file tree

Showing 17 changed files with 18 additions and 16 deletions.
diff --git a/.DS_Store b/.DS_Store
diff --git a/Backpropagation.ipynb b/Backpropagation.ipynb
@@ -223,7 +223,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.18"
+   "version": "3.12.4"
   }
  },
  "nbformat": 4,

diff --git a/Perceptron.ipynb b/Perceptron.ipynb
@@ -532,7 +532,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.18"
+   "version": "3.12.4"
   }
  },
  "nbformat": 4,

diff --git a/Slides/.DS_Store b/Slides/.DS_Store
diff --git a/Slides/Backpropagation_1.pdf b/Slides/Backpropagation_1.pdf
diff --git a/Data/.DS_Store → _extensions/.DS_Store b/Data/.DS_Store → _extensions/.DS_Store
diff --git a/docs/Backpropagation.html b/docs/Backpropagation.html
@@ -2,7 +2,7 @@
 <html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
 
 <meta charset="utf-8">
-<meta name="generator" content="quarto-1.5.56">
+<meta name="generator" content="quarto-1.5.57">
 
 <meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
 
@@ -228,7 +228,7 @@
 }
 
 // Store cell data
-globalThis.qpyodideCellDetails = [{"options":{"results":"markup","fig-height":5,"classes":"","output":"true","warning":"true","message":"true","autorun":"","read-only":"false","comment":"","fig-cap":"","dpi":72,"context":"interactive","label":"","out-width":"700px","out-height":"","fig-width":7},"code":"import numpy as np\nimport matplotlib.pyplot as plt\nimport pandas as pd","id":1},{"options":{"results":"markup","fig-height":5,"classes":"","output":"true","warning":"true","message":"true","autorun":"","read-only":"false","comment":"","fig-cap":"","dpi":72,"context":"interactive","label":"","out-width":"700px","out-height":"","fig-width":7},"code":"df = pd.read_csv(\"https://raw.githubusercontent.com/Mark-Kramer/BU-MA665-MA666/master/Data/backpropagation_example_data.csv\")\n\n# Extract the variables from the loaded data\nin_true = np.array(df.iloc[:,0])  #Get the values associated with the first column of the dataframe\nout_true = np.array(df.iloc[:,1])  #Get the values associated with the second column of the dataframe","id":2},{"options":{"results":"markup","fig-height":5,"classes":"","output":"true","warning":"true","message":"true","autorun":"","read-only":"false","comment":"","fig-cap":"","dpi":72,"context":"interactive","label":"","out-width":"700px","out-height":"","fig-width":7},"code":"print(np.transpose([in_true, out_true]))","id":3},{"options":{"results":"markup","fig-height":5,"classes":"","output":"true","warning":"true","message":"true","autorun":"","read-only":"false","comment":"","fig-cap":"","dpi":72,"context":"interactive","label":"","out-width":"700px","out-height":"","fig-width":7},"code":"def sigmoid(x):\n    return 1/(1+np.exp(-x))     # Define the sigmoid anonymous function.\n\ndef feedforward(w, s0):         # Define feedforward solution.\n    x1 = w[0]*s0                # ... activity of first neuron,\n    s1 = sigmoid(x1)            # ... output of first neuron,\n    x2 = w[1]*s1                # ... activity of second neuron,\n    s2 = sigmoid(x2)            # ... output of second neuron,\n    out= w[2]                   # Output of neural network.\n    return out,s1,s2","id":4},{"options":{"results":"markup","fig-height":5,"classes":"","output":"true","warning":"true","message":"true","autorun":"","read-only":"false","comment":"","fig-cap":"","dpi":72,"context":"interactive","label":"","out-width":"700px","out-height":"","fig-width":7},"code":"w     = [0.5,0.5]                  # Choose initial values for the weights.\nalpha = 0.01                    # Set the learning constant.\n\nK = np.size(in_true);\nresults = np.zeros([K,3])        # Define a variable to hold the results of each iteration.    \n\nfor k in np.arange(K):\n    s0     = in_true[k]          # Define the input,\n    target = out_true[k]         # ... and the target output.\n    \n    #Step 2. Calculate feedforward solution to get output.\n    \n    #Step 3. Update the weights.\n    w0 = w[0]; w1 = w[1];\n    w[1] = \"SOMETHING\"\n    w[0] = \"SOMETHING\"\n    \n    # Save the results of this step. --------------------------------------\n    # Here we save the 3 weights, and the neural network output.\n    # results[k,:] = [w[0],w[1],  out]\n\n# Plot the NN weights and error during training \n# plt.clf()\n# plt.plot(results[:,1], label='w1')\n# plt.plot(results[:,0], label='w0')\n# plt.plot(results[:,2]-target, label='error')\n# plt.legend()                       #Include a legend,\n# plt.xlabel('Iteration number');    #... and axis label.\n\n# Print the NN weights\n# print(results[-1,0:2])","id":5}];
+globalThis.qpyodideCellDetails = [{"code":"import numpy as np\nimport matplotlib.pyplot as plt\nimport pandas as pd","options":{"classes":"","out-width":"700px","warning":"true","fig-width":7,"context":"interactive","label":"","results":"markup","autorun":"","output":"true","fig-height":5,"out-height":"","dpi":72,"comment":"","message":"true","fig-cap":"","read-only":"false"},"id":1},{"code":"df = pd.read_csv(\"https://raw.githubusercontent.com/Mark-Kramer/BU-MA665-MA666/master/Data/backpropagation_example_data.csv\")\n\n# Extract the variables from the loaded data\nin_true = np.array(df.iloc[:,0])  #Get the values associated with the first column of the dataframe\nout_true = np.array(df.iloc[:,1])  #Get the values associated with the second column of the dataframe","options":{"classes":"","out-width":"700px","warning":"true","fig-width":7,"context":"interactive","label":"","results":"markup","autorun":"","output":"true","fig-height":5,"out-height":"","dpi":72,"comment":"","message":"true","fig-cap":"","read-only":"false"},"id":2},{"code":"print(np.transpose([in_true, out_true]))","options":{"classes":"","out-width":"700px","warning":"true","fig-width":7,"context":"interactive","label":"","results":"markup","autorun":"","output":"true","fig-height":5,"out-height":"","dpi":72,"comment":"","message":"true","fig-cap":"","read-only":"false"},"id":3},{"code":"def sigmoid(x):\n    return 1/(1+np.exp(-x))     # Define the sigmoid anonymous function.\n\ndef feedforward(w, s0):         # Define feedforward solution.\n    x1 = w[0]*s0                # ... activity of first neuron,\n    s1 = sigmoid(x1)            # ... output of first neuron,\n    x2 = w[1]*s1                # ... activity of second neuron,\n    s2 = sigmoid(x2)            # ... output of second neuron,\n    out= w[2]                   # Output of neural network.\n    return out,s1,s2","options":{"classes":"","out-width":"700px","warning":"true","fig-width":7,"context":"interactive","label":"","results":"markup","autorun":"","output":"true","fig-height":5,"out-height":"","dpi":72,"comment":"","message":"true","fig-cap":"","read-only":"false"},"id":4},{"code":"w     = [0.5,0.5]                  # Choose initial values for the weights.\nalpha = 0.01                    # Set the learning constant.\n\nK = np.size(in_true);\nresults = np.zeros([K,3])        # Define a variable to hold the results of each iteration.    \n\nfor k in np.arange(K):\n    s0     = in_true[k]          # Define the input,\n    target = out_true[k]         # ... and the target output.\n    \n    #Step 2. Calculate feedforward solution to get output.\n    \n    #Step 3. Update the weights.\n    w0 = w[0]; w1 = w[1];\n    w[1] = \"SOMETHING\"\n    w[0] = \"SOMETHING\"\n    \n    # Save the results of this step. --------------------------------------\n    # Here we save the 3 weights, and the neural network output.\n    # results[k,:] = [w[0],w[1],  out]\n\n# Plot the NN weights and error during training \n# plt.clf()\n# plt.plot(results[:,1], label='w1')\n# plt.plot(results[:,0], label='w0')\n# plt.plot(results[:,2]-target, label='error')\n# plt.legend()                       #Include a legend,\n# plt.xlabel('Iteration number');    #... and axis label.\n\n# Print the NN weights\n# print(results[-1,0:2])","options":{"classes":"","out-width":"700px","warning":"true","fig-width":7,"context":"interactive","label":"","results":"markup","autorun":"","output":"true","fig-height":5,"out-height":"","dpi":72,"comment":"","message":"true","fig-cap":"","read-only":"false"},"id":5}];
 
 
 </script>