BuboFlash - helps with learning

Edited, memorised or added to reading queue

Do you want BuboFlash to help you learning these things? Click here to log in or create user.

Flashcard 7625143094540

Tags

#deep-learning #keras #lstm #python #sequence

Question

Careful choice must be given to the number of [...] specified when preparing your input data for sequence prediction problems in Keras

Answer

time steps

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Parent (intermediate) annotation

Open it
Careful choice must be given to the number of time steps specified when preparing your input data for sequence prediction problems in Keras

Original toplevel document (pdf)

cannot see any pdfs

Flashcard 7625145715980

Tags

#recurrent-neural-networks #rnn

Question

The challenge to derive such individual-level predictions is particularly demanding in the context of non-contractual settings (such as most [...] businesses, online media consumption, charity donations).

Answer

retail

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Parent (intermediate) annotation

Open it
The challenge to derive such individual-level predictions is particularly demanding in the context of non-contractual settings (such as most retail businesses, online media consumption, charity donations).

Original toplevel document (pdf)

cannot see any pdfs

Flashcard 7625148599564

Tags

#tensorflow #tensorflow-certificate

Question

print('Datatype of every element:', A.dtype)
print('Number of dimensions (rank):', A.ndim)
print('Shape of tensor:', A.shape)
print('Elements along the 0 axis:', A.shape[0])
print('Elements along the last axis:',  [...])
print('Total number of elements:', tf.size(A))
print('Total number of elements:', tf.size(A).numpy())


Output:
Datatype of every element: <dtype: 'int64'>
Number of dimensions (rank): 4
Shape of tensor: (2, 3, 4, 5)
Elements along the 0 axis: 2
Elements along the last axis: 5
Total number of elements: tf.Tensor(120, shape=(), dtype=int32)
Total number of elements: 120

Answer

A.shape[-1]

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Properties of tensor
every element:', A.dtype) print('Number of dimensions (rank):', A.ndim) print('Shape of tensor:', A.shape) print('Elements along the 0 axis:', A.shape[0]) print('Elements along the last axis:', <span>A.shape[-1]) print('Total number of elements:', tf.size(A)) print('Total number of elements:', tf.size(A).numpy()) Output: Datatype of every element: <dtype: 'int64'> Number of dimensions (ra

Flashcard 7625150434572

Tags

#algebra #matrix #tensorflow #tensorflow-certificate

Question

In General:

To multiply an m×n matrix by an n×p matrix, the ns must be [...],
and the result is an m×p matrix.

Answer

the same

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Matrix multiplication
In General: To multiply an m×n matrix by an n×p matrix, the ns must be the same, and the result is an m×p matrix.

Flashcard 7625152793868

Tags

#conv2D #convolution #tensorflow #tensorflow-certificate

Question

Step 1 is to gather the data. You'll notice that there's a bit of a change here in that the training data needed to be reshaped. That's because the first convolution expects a [...] containing everything, so instead of 60,000 28x28x1 items in a list, we have a single 4D list that is 60,000x28x28x1,

Answer

single tensor

status	not learned	measured difficulty	37% [default]	last interval [days]
repetition number in this series	0	memorised on		scheduled repetition
scheduled repetition interval		last repetition or drill

Parent (intermediate) annotation

Open it
Step 1 is to gather the data. You'll notice that there's a bit of a change here in that the training data needed to be reshaped. That's because the first convolution expects a single tensor containing everything, so instead of 60,000 28x28x1 items in a list, we have a single 4D list that is 60,000x28x28x1,

Original toplevel document

Convolution Neural Network - introduction
Step 1 is to gather the data. You'll notice that there's a bit of a change here in that the training data needed to be reshaped. That's because the first convolution expects a single tensor containing everything, so instead of 60,000 28x28x1 items in a list, we have a single 4D list that is 60,000x28x28x1, and the same for the test images. If you don't do this, you'll get an error when training as the Convolutions do not recognize the shape. import tensorflow as tf mnist = tf.keras.datase

Edited, memorised or added to reading queue

on 23-Apr-2024 (Tue)

Flashcard 7625143094540

Parent (intermediate) annotation

Original toplevel document (pdf)

Flashcard 7625145715980

Parent (intermediate) annotation

Original toplevel document (pdf)

Flashcard 7625148599564

Flashcard 7625150434572

Flashcard 7625152793868

Parent (intermediate) annotation

Original toplevel document