An early approach to finding a line for our classifier. The Perceptron Algorithm describes this early technique for improving our classification line.
We now come to understand that an error function is what is needed to get an estimation of how good or bad our line is. So there is some reference here to the Error Function.
Then inevitably we start talking about a new type of Activation Function that will replace our Step Function. This is the Sigmoid Activation Function for Binary classification and the SoftMax Activation Function for multi-class classification.
★ Watch the entire Playlist here: https://www.youtube.com/playlist?list=PLp_FpnyDwvuCU1GN376wUXG8vROXAtiFn
_______
🏠 Website → https://anifantakis.eu
🎬 All Videos: https://anifantakis.eu/videos/
🕮 All Articles: https://anifantakis.eu/articles/
✅ Subscribe for more videos → https://youtube.com/ioannisanifantakis
👍 Follow me
• LinkedIn: https://www.linkedin.com/in/anifantakis/
• Medium: https://ioannisanif.medium.com/
• Twitter: https://twitter.com/ioannisa
• GitHub: https://github.com/ioannisa
_______
#DeepLearning #Perceptron #ErrorFunctions #Sigmoid #SoftMax #NeuralNetworks
