Karteikarten
Ohne Titel
Karten in diesem Stapel (16)
- 1Zfunction for linear combination of inputs/weights/bias
- 2sigmoidfunction that converts Z into 0,1
tanh into -1,0,1
Relu into 0,Z
Leaqky relu into 0.01,Z - 3tanh/relu/leaky relulike sigmoid function, it converts Z into -1,0,1.
- 4RNNrecurrent neural network that is based on the order of sequence of data - used on data like speech, or music
- 5weightparameter that represents strength of one neuron to another
- 6cost function/loss function/objective functionmeasures difference between predicted output and true output
- 7back propagationalgorithm used to minimize cost function CALCULATES gradients (partial derivatives). It is a step in optimization.
- 8n^[l]subscript_(h)n = neuron
l = layer
h = specific neuron in lth layer - 9Xinput data matrix
- 10gradient descentalgorithm used to minimize cost function, USES gradients (partial derivates)
- 11WWeight
- 12bBias
- 13aa=activation_function(weighted_sum+bias)
- 14y-hatPredicted output
- 15Pprobability (function given y)
- 16initializationwhat you set the parameters (weights and bias) to before training.
Informationen
- Beschreibung
- Karteikarten am Ohne Titel, erstellt von mark fabian am 01/02/2024.
- Erstellt von
- mark fabian
- Aufrufe
- 0
- Bewertung