Hi,

my LSTM_backward keeps on outputting values removed from expected ones even though my LSTM_cell_backward seems to output the right ones.

I simply cannot understand what I may be doing wrong.

```
# UNGRADED FUNCTION: lstm_backward
def lstm_backward(da, caches):
"""
Implement the backward pass for the RNN with LSTM-cell (over a whole sequence).
Arguments:
da -- Gradients w.r.t the hidden states, numpy-array of shape (n_a, m, T_x)
caches -- cache storing information from the forward pass (lstm_forward)
Returns:
gradients -- python dictionary containing:
dx -- Gradient of inputs, of shape (n_x, m, T_x)
da0 -- Gradient w.r.t. the previous hidden state, numpy array of shape (n_a, m)
dWf -- Gradient w.r.t. the weight matrix of the forget gate, numpy array of shape (n_a, n_a + n_x)
dWi -- Gradient w.r.t. the weight matrix of the update gate, numpy array of shape (n_a, n_a + n_x)
dWc -- Gradient w.r.t. the weight matrix of the memory gate, numpy array of shape (n_a, n_a + n_x)
dWo -- Gradient w.r.t. the weight matrix of the output gate, numpy array of shape (n_a, n_a + n_x)
dbf -- Gradient w.r.t. biases of the forget gate, of shape (n_a, 1)
dbi -- Gradient w.r.t. biases of the update gate, of shape (n_a, 1)
dbc -- Gradient w.r.t. biases of the memory gate, of shape (n_a, 1)
dbo -- Gradient w.r.t. biases of the output gate, of shape (n_a, 1)
"""
# Retrieve values from the first cache (t=1) of caches.
(caches, x) = caches
(a1, c1, a0, c0, f1, i1, cc1, o1, x1, parameters) = caches[0]
### START CODE HERE ###
{*Moderator's Edit: Solution Code Removed*}
### END CODE HERE ###
# Store the gradients in a python dictionary
gradients = {"dx": dx, "da0": da0, "dWf": dWf,"dbf": dbf, "dWi": dWi,"dbi": dbi,
"dWc": dWc,"dbc": dbc, "dWo": dWo,"dbo": dbo}
return gradients
```

```
gradients["dx"][1][2] = [-0.00424213 0.28205375 -0.48292508 -0.43281115]
gradients["dx"].shape = (3, 10, 4)
gradients["da0"][2][3] = 0.36036164521813085
gradients["da0"].shape = (5, 10)
gradients["dWf"][3][1] = -0.185172422655972
gradients["dWf"].shape = (5, 8)
gradients["dWi"][1][2] = 0.4051243309298186
gradients["dWi"].shape = (5, 8)
gradients["dWc"][3][1] = -0.07937467355121491
gradients["dWc"].shape = (5, 8)
gradients["dWo"][1][2] = 0.03894877576298697
gradients["dWo"].shape = (5, 8)
gradients["dbf"][4] = [-0.17049796]
gradients["dbf"].shape = (5, 1)
gradients["dbi"][4] = [-0.50848333]
gradients["dbi"].shape = (5, 1)
gradients["dbc"][4] = [-0.42510818]
gradients["dbc"].shape = (5, 1)
gradients["dbo"][4] = [-0.17958196]
gradients["dbo"].shape = (5, 1)
```

```
Expected Output:
gradients["dx"][1][2] = [0.00218254 0.28205375 -0.48292508 -0.43281115]
gradients["dx"].shape = (3, 10, 4)
gradients["da0"][2][3] = 0.312770310257
gradients["da0"].shape = (5, 10)
gradients["dWf"][3][1] = -0.0809802310938
gradients["dWf"].shape = (5, 8)
gradients["dWi"][1][2] = 0.40512433093
gradients["dWi"].shape = (5, 8)
gradients["dWc"][3][1] = -0.0793746735512
gradients["dWc"].shape = (5, 8)
gradients["dWo"][1][2] = 0.038948775763
gradients["dWo"].shape = (5, 8)
gradients["dbf"][4] = [-0.15745657]
gradients["dbf"].shape = (5, 1)
gradients["dbi"][4] = [-0.50848333]
gradients["dbi"].shape = (5, 1)
gradients["dbc"][4] = [-0.42510818]
gradients["dbc"].shape = (5, 1)
gradients["dbo"][4] = [ -0.17958196]
gradients["dbo"].shape = (5, 1)
```

```
# UNGRADED FUNCTION: lstm_cell_backward
def lstm_cell_backward(da_next, dc_next, cache):
"""
Implement the backward pass for the LSTM-cell (single time-step).
Arguments:
da_next -- Gradients of next hidden state, of shape (n_a, m)
dc_next -- Gradients of next cell state, of shape (n_a, m)
cache -- cache storing information from the forward pass
Returns:
gradients -- python dictionary containing:
dxt -- Gradient of input data at time-step t, of shape (n_x, m)
da_prev -- Gradient w.r.t. the previous hidden state, numpy array of shape (n_a, m)
dc_prev -- Gradient w.r.t. the previous memory state, of shape (n_a, m, T_x)
dWf -- Gradient w.r.t. the weight matrix of the forget gate, numpy array of shape (n_a, n_a + n_x)
dWi -- Gradient w.r.t. the weight matrix of the update gate, numpy array of shape (n_a, n_a + n_x)
dWc -- Gradient w.r.t. the weight matrix of the memory gate, numpy array of shape (n_a, n_a + n_x)
dWo -- Gradient w.r.t. the weight matrix of the output gate, numpy array of shape (n_a, n_a + n_x)
dbf -- Gradient w.r.t. biases of the forget gate, of shape (n_a, 1)
dbi -- Gradient w.r.t. biases of the update gate, of shape (n_a, 1)
dbc -- Gradient w.r.t. biases of the memory gate, of shape (n_a, 1)
dbo -- Gradient w.r.t. biases of the output gate, of shape (n_a, 1)
"""
# Retrieve information from "cache"
(a_next, c_next, a_prev, c_prev, ft, it, cct, ot, xt, parameters) = cache
### START CODE HERE ###
{*Moderator's Edit: Solution Code Removed*}
### END CODE HERE ###
# Save gradients in dictionary
gradients = {"dxt": dxt, "da_prev": da_prev, "dc_prev": dc_prev, "dWf": dWf,"dbf": dbf, "dWi": dWi,"dbi": dbi,
"dWc": dWc,"dbc": dbc, "dWo": dWo,"dbo": dbo}
return gradients
```

```
gradients["dxt"][1][2] = 3.2305591151091875
gradients["dxt"].shape = (3, 10)
gradients["da_prev"][2][3] = -0.06396214197109236
gradients["da_prev"].shape = (5, 10)
gradients["dc_prev"][2][3] = 0.7975220387970015
gradients["dc_prev"].shape = (5, 10)
gradients["dWf"][3][1] = -0.1479548381644968
gradients["dWf"].shape = (5, 8)
gradients["dWi"][1][2] = 1.0574980552259903
gradients["dWi"].shape = (5, 8)
gradients["dWc"][3][1] = 2.3045621636876668
gradients["dWc"].shape = (5, 8)
gradients["dWo"][1][2] = 0.3313115952892109
gradients["dWo"].shape = (5, 8)
gradients["dbf"][4] = [0.18864637]
gradients["dbf"].shape = (5, 1)
gradients["dbi"][4] = [-0.40142491]
gradients["dbi"].shape = (5, 1)
gradients["dbc"][4] = [0.25587763]
gradients["dbc"].shape = (5, 1)
gradients["dbo"][4] = [0.13893342]
gradients["dbo"].shape = (5, 1)
```

```
Expected Output:
gradients["dxt"][1][2] = 3.23055911511
gradients["dxt"].shape = (3, 10)
gradients["da_prev"][2][3] = -0.0639621419711
gradients["da_prev"].shape = (5, 10)
gradients["dc_prev"][2][3] = 0.797522038797
gradients["dc_prev"].shape = (5, 10)
gradients["dWf"][3][1] = -0.147954838164
gradients["dWf"].shape = (5, 8)
gradients["dWi"][1][2] = 1.05749805523
gradients["dWi"].shape = (5, 8)
gradients["dWc"][3][1] = 2.30456216369
gradients["dWc"].shape = (5, 8)
gradients["dWo"][1][2] = 0.331311595289
gradients["dWo"].shape = (5, 8)
gradients["dbf"][4] = [ 0.18864637]
gradients["dbf"].shape = (5, 1)
gradients["dbi"][4] = [-0.40142491]
gradients["dbi"].shape = (5, 1)
gradients["dbc"][4] = [ 0.25587763]
gradients["dbc"].shape = (5, 1)
gradients["dbo"][4] = [ 0.13893342]
gradients["dbo"].shape = (5, 1)
```