small change in 03_ml_basics_simple_neural_network.ipynb
This commit is contained in:
parent
75949cf50c
commit
3e5093515f
File diff suppressed because one or more lines are too long
@ -23,6 +23,7 @@
|
|||||||
]
|
]
|
||||||
},
|
},
|
||||||
{
|
{
|
||||||
|
"attachments": {},
|
||||||
"cell_type": "markdown",
|
"cell_type": "markdown",
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"source": [
|
"source": [
|
||||||
@ -76,7 +77,7 @@
|
|||||||
"\n",
|
"\n",
|
||||||
"Note, that it is assumed that the activation function is a sigmoid with the derivative\n",
|
"Note, that it is assumed that the activation function is a sigmoid with the derivative\n",
|
||||||
"\n",
|
"\n",
|
||||||
"$$ \\sigma(x) * (1 - \\sigma(x)) $$\n",
|
"$$ \\sigma(x) \\cdot (1 - \\sigma(x)) $$\n",
|
||||||
"\n",
|
"\n",
|
||||||
"Applying the chain rule further, we obtain the gradient for the weights from the input layer to the hidden layer: \n",
|
"Applying the chain rule further, we obtain the gradient for the weights from the input layer to the hidden layer: \n",
|
||||||
"\n",
|
"\n",
|
||||||
|
Loading…
Reference in New Issue
Block a user