editing some files

1 - The_method_of_least_squares.ipynb

@@ -0,0 +1 @@
+{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"#source: https://github.com/llSourcell/linear_regression_live/blob/master/demo.py\ndef compute_error_for_line_given_points(b, m, coordinates):\n    \"\"\"\n    For a given line, (defined by the equation below) \n    and a given set of coordinates, comprising a list of two-element sublists,  \n    produce the error, which is the sum of the square of the discrepancies from the line.  \n    Equation of line: y = mx + b\n    where m is the slope, and b is the y-intercept\n    \"\"\"\n    totalError = 0 # Initialize sum of discrepancies to naught.\n    for i in range(0, len(coordinates)): # Sweep over pairs inthe list of coordinates.\n        x = coordinates[i][0] # Select the first number in the ith cooirdinate pair in the list.\n        y = coordinates[i][1] # Select the second number in the ith cooirdinate pair in the list.\n        totalError += (y - (m * x + b)) ** 2 # Add to the sum, the square of the discrepancy between the *predicted* y value (of the line equation) and the *actual* y value (of the coordinate).\n    result = totalError / float(len(coordinates)) # Divide the total sum of squares-of-discrepancies by number of pairs in the list, to arrive at the average. \n    return result\n# example \nb = 1\nm = 2\ncoordinates = [[3,6],[6,9],[12,18]]\ncompute_error_for_line_given_points(b, m, coordinates)","execution_count":7,"outputs":[{"output_type":"execute_result","execution_count":7,"data":{"text/plain":"22.0"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib as plt\n\nplt.[[3,6],[6,9],[12,18]]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.help()","execution_count":6,"outputs":[{"output_type":"error","ename":"AttributeError","evalue":"module 'matplotlib' has no attribute 'help'","traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)","\u001b[0;32m<ipython-input-6-34987296d359>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhelp\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m","\u001b[0;31mAttributeError\u001b[0m: module 'matplotlib' has no attribute 'help'"]}]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.1"}},"nbformat":4,"nbformat_minor":1}

3 - Linear_regression.ipynb

@@ -0,0 +1 @@
+{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"#source: https://github.com/llSourcell/linear_regression_live/blob/master/demo.py\n\n# A list of sublists each of which has two elements;\n# the first being the price of wheat/kg and\n# the second being the average price of bread.\nprice_wheat_bread = [[0.5,5],\n                     [0.6,5.5],\n                     [0.8,6],\n                     [1.1,6.8],\n                     [1.4,7]\n                    ]\n\ndef step_gradient(b_current, \n                  m_current, \n                  points, \n                  learningRate):\n    \"\"\"\n    For a given y-intercept, b, and slope, m, and set of points, and learning rate, \n    produce the step size of the gradient needed for changing those coefficients, b and m.\n    \"\"\"\n    b_gradient = 0 # Initialize change in slope to naught, i.e. no change.\n    m_gradient = 0 # Initialize change in y-intercept to naught, i.e. no change. \n    N = float(len(points)) # The number of pairs of points in our list of coordinates.\n    for i in range(0, len(points)): # Sweep over the index of every pair of points in the list of coordinates.\n        x = points[i][0] # Select the first number in the ith pair.\n        y = points[i][1] # Select the second number in the ith pair.\n        # How quickly does the squared error change with respect to the y-intercept?\n        # The negative sign means that the gradient points in the direction of decrease of error, instead of increase.\n        b_gradient += -(2/N) * (y - ((m_current * x) + b_current)) # Notice the two comes down based on the power rule of derivatives.\n        # How quickly does the error change with respect to the slope?\n        m_gradient += -(2/N) * x * (y - ((m_current * x) + b_current)) # Notice the x comes out based on the rule of derivatives.\n    # Based on how large of steps you chose to to increment, the gradients (or negative of the slopes) are now used to adjust the old values.\n    new_b = b_current - (learningRate * b_gradient) # I am not sure why there is a negative sign.\n    new_m = m_current - (learningRate * m_gradient) # \n    return [new_b, new_m]\n\ndef gradient_descent_runner(points, \n                            starting_b, \n                            starting_m, \n                            learning_rate, \n                            num_iterations):\n    \"\"\"\n    Given a set of points, and initial values of b and m, and a learning rate, and number of iterations,\n    produce a...what?\n    \"\"\"\n    b = starting_b\n    m = starting_m\n    for i in range(num_iterations): # How ever many times you want to run the gradient descent, that's how many increments will change your coefficients, m and b, to readjust the predicting line, with successively less and less error.\n        b, m = step_gradient(b, m, points, learning_rate)\n    return [b, m]\n\n# Let's produce the best m and b values, given initial choices of m as 12, b as 42, \n# and the increment learning step as .01, over 10000 iterations.\n# The goal being to end up with ideal, or at least very accurate, coefficients.\ngradient_descent_runner(price_wheat_bread, 12, 42, 0.01, 10000) \n","execution_count":17,"outputs":[{"output_type":"execute_result","execution_count":17,"data":{"text/plain":"[4.107202463019789, 2.2190814997453208]"},"metadata":{}}]},{"metadata":{},"cell_type":"markdown","source":"Apparently the ideal value of b (y-intercept) is 4.1 and of m (slope) is 2.2"},{"metadata":{"collapsed":true,"trusted":false},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":2},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython2","version":"2.7.13"}},"nbformat":4,"nbformat_minor":1}

README.md

@@ -2,12 +2,12 @@
 
 There are six snippets of code that made deep learning what it is today. [Coding the History of Deep Learning](https://medium.com/@emilwallner/the-history-of-deep-learning-explored-through-6-code-snippets-d0a0e8545202) covers the inventors and the background to their breakthroughs. In this repo, you can find all the code samples from the story.
 
-- **The Method of Least Squares**: The first cost function
-- **Gradient Descent**: Finding the minimum of the cost function
-- **Linear Regression**: Automatically decrease the cost function
-- **The Perceptron**: Using a linear regression type equations to mimic a neuron
-- **Artificial Neural Networks**: Leveraging backpropagation to solve non-linear problems
-- **Deep Neural Networks**: Neural networks with more than one hidden layer
+1. **The Method of Least Squares**: The first cost function
+1. **Gradient Descent**: Finding the minimum of the cost function
+1. **Linear Regression**: Automatically decrease the cost function
+1. **The Perceptron**: Using a linear regression type equations to mimic a neuron
+1. **Artificial Neural Networks**: Leveraging backpropagation to solve non-linear problems
+1. **Deep Neural Networks**: Neural networks with more than one hidden layer