Softmax and cross entropy
The model produces three numbers. How do they turn into probabilities, and why do we take a logarithm instead of a square when measuring the error?
4 steps
150 XP
A free account is needed
Start the lesson →
Sources
- Bishop, C. M. 2006 · Pattern Recognition and Machine Learning, Bölüm 4.3.4 ve 5.2 · Springer
- Goodfellow, Bengio, Courville 2016 · Deep Learning, Bölüm 6.2.2 · MIT Press
- Zhang, A. et al. 2022 · Derin Öğrenmeye Dalış, Bölüm 4.1 · d2l.ai
ML Academy · an interactive machine learning course that runs in your browser ·
All lessons