An Introduction to Convolutional Neural Networks
Background
Computational models of neural networks have been around for more than half a century, beginning with the simple model that McCulloch and Pitts developed in 1943 [1]. Hebb subsequently contributed a learning algorithm to train such models [2], summed up by the familiar refrain: 'Neuron that fire together, wire together'. Hebb's rule, and a popular variant known as the Delta rule, were crucial for early models of cognition, but they quickly ran into trouble with respect to their computational power. In their extremely influencial book, Perceptrons, Minsky and Papert proved that these networks couldn't even learn the boolean XOR function, due to due only being able to learn a single layer of weights. Luckily, a more complex learning algorithm, backpropagation, eventually emerged
Subsection
Using more "equals" (=) signs creates a subsection.
A smaller subsection
Don't skip levels, like from two to four equals signs.
Start with 2 equals signs not 1 because 1 creates H1 tags which should be reserved for page title.
Section headings
Headings organize your writing into sections. The Wiki software can automatically generate a table of contents from them.
Subsection
Using more "equals" (=) signs creates a subsection.
A smaller subsection
Don't skip levels, like from two to four equals signs.
Start with 2 equals signs not 1 because 1 creates H1 tags which should be reserved for page title.
References
- McCulloch, Warren; Walter Pitts (1943). "A Logical Calculus of Ideas Immanent in Nervous Activity". Bulletin of Mathematical Biophysics 5 (4): 115–133.
- Hebb, Donald (1949). The Organization of Behavior. New York: Wiley.