Calculating slopes
You're now going to practice calculating slopes. When plotting the mean-squared error loss function against predictions, the slope is 2 * x * (xb-y), or 2 * input_data * error. Note that x and b may have multiple numbers (x is a vector for each data point, and b is a vector). In this case, the output will also be a vector, which is exactly what you want.
You're ready to write the code to calculate this slope while using a single data point. You'll use pre-defined weights called weights as well as data for a single point called input_data. The actual value of the target you want to predict is stored in target.
This is a part of the course
“Introduction to Deep Learning in Python”
Exercise instructions
- Calculate the predictions,
preds, by multiplyingweightsby theinput_dataand computing their sum. - Calculate the error, which is
predsminustarget. Notice that this error corresponds toxb-yin the gradient expression. - Calculate the slope of the loss function with respect to the prediction. To do this, you need to take the product of
input_dataanderrorand multiply that by2.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Calculate the predictions: preds
preds = ____
# Calculate the error: error
error = ____ - ____
# Calculate the slope: slope
slope = ____ * ____ * ____
# Print the slope
print(slope)