Question 1
Correct
Note de 1,00 sur 1,00
To which of these tasks would you apply a many-to-one RNN architecture? (Check all that apply).
A. Gender recognition from speech
B. Sentiment classication (input a piece of text and output a 0/1 to denote positive or negative
sentiment)
C. Image classication
D. Machine Translation (input a piece of text and the output is a translated text)
Votre réponse est correcte.
Les réponses correctes sont :
Sentiment classication (input a piece of text and output a 0/1 to denote positive or negative sentiment),
Gender recognition from speech
Question 2
Correct
Note de 1,00 sur 1,00
Consider this RNN: This specic type of architecture is appropriate when:
A.
T < T
y
x
B. T = Ty
x
C. T > T
y
x
D.
T = T =1
y
x
Votre réponse est correcte.
La réponse correcte est :
T = Ty
x
Question 3
Correct
Note de 1,00 sur 1,00
You have nished training a language model RNN and are using it to sample random sentences, as
follows:
What are you doing at each time step t:
A. (1) Pick the highest probability from the output probabilities of the RNN for the time step
, (2) the selected word is passed to the next step t+1.
B. (1) Randomly sample a chosen word according to the given output probabilties of the RNN for
the time step
, (2) the selected word is passed to the next step t+1.
C.
D.
(1) Use the probabilities given by the RNN to sample a word for the time step
, (2) the
ground truth word from the training set is passed to the next step t+1.
(1) The highest probability word of the time step t as
is picked from output probabilities,
(2) the ground truth word from the training set is passed to the next step t+1.
Votre réponse est correcte.
La réponse correcte est :
(1) Randomly sample a chosen word according to the given output probabilties of the RNN for the time step
, (2) the selected word is passed to the next step t+1.
Question 4
Partiellement correct
Note de 0,67 sur 1,00
Which of these is the most likely cause of problems for RNNs:
A. Exploding gradients.
B. Vanishing gradients.
C. Dicult to process longer sequences.
D. Activations are too large.
Votre réponse est partiellement correcte.
Publicité
Vous en avez sélectionné correctement 2.
Les réponses correctes sont :
Exploding gradients.,
Vanishing gradients.,
Dicult to process longer sequences.
Question 5
Correct
Note de 1,00 sur 1,00
The Gated Recurrent Units (GRU) helps avoiding vanishing/exploding gradients
Where:
Check all that apply.
A. z is a gating vector that determines how much of the past information should be passed along to
t
the future and it depends on the reset gate vector r
t
B. The reset gate r is used to decide how much of the past information to forget.
t
C. The nal output state h is a combination of h and ϕ (W x +U (r ⊙h )+b ) via z and it is the
t−1
h t
h t
t−1
t
t
h
h
representation of the input x
t
D. The nal output state h is a combination of h and ϕ (W x +U (r ⊙h )+b ) via z and it is the
t−1
h t
h t
t−1
t
t
h
h
representation of the hidden state h
t -1
Votre réponse est correcte.
Les réponses correctes sont :
The nal output state h is a combination of h and ϕ (W x +U (r ⊙h )+b ) via z and it is the
t−1
h t
h t
t−1
t
t
h
h
representation of the input x ,
t
The reset gate r is used to decide how much of the past information to forget.
t
Question 6
Correct
Note de 1,00 sur 1,00
Join the RNN architecture to the right application:
Many-to-many
Many-to-many
Many-to-one
Name entity recognitionMachine translationSentiment classicationOne-to-one
One-to-many
Votre réponse est correcte.
La réponse correcte est :
Many-to-many
Publicité
Many-to-many
→ Name entity recognition,
Traditional neural networkMusic generationMany-to-one
One-to-one
One-to-many
→ Machine translation,
→ Sentiment classication,
→ Traditional neural network,
→ Music generation
Question 7
Correct
Note de 1,00 sur 1,00
Join the gure to the right activation function:
Votre réponse est correcte.
La réponse correcte est :
SigmoidRELUTanh → Sigmoid,
→ RELU,
→ Tanh
Question 8
Correct
Note de 1,00 sur 1,00
What is true about RNN (check all that apply)
A. Computation takes into account historical information
B. Can consider any future input for the current state
C. Weights are shared across time
D. Possibility of processing input of any length
Votre réponse est correcte.
Les réponses correctes sont :
Possibility of processing input of any length,
Computation takes into account historical information,
Weights are shared across time
Question 9
Correct
Note de 1,00 sur 1,00
You are training an RNN, and nd that your weights and activations are all taking on the value of NaN
(“Not a Number”). Which of these is the most likely cause of this problem?
A. Vanishing gradient problem
B. Exploding gradient problem
Votre réponse est correcte.
La réponse correcte est :
Exploding gradient problem
Question 10
Correct
Note de 1,00 sur 1,00
Then evne the world "Ecstatic" does not appear in your training set, the RNN might reasonably be
expected to recognize "I'm ecstatic" as deserving the label=1
A. False
B. True
Votre réponse est correcte.
La réponse correcte est :
True
Question 11
Correct
Note de 1,00 sur 1,00
Suppose you are training a LSTM. You have a 10000 word vocabulary, and are using an LSTM with 100-
dimensional activations a<t>. What is the dimension of Update gate Γ at each time step?
u
A. 10000
B. 10
C. 100
D. 100000
Votre réponse est correcte.
La réponse correcte est :
100
Question 12
Partiellement correct
Publicité
Note de 0,67 sur 1,00
Some word embedding techniques are:
a. Skip-gram
b. GloVe
c. Word2vec
d. GliVer
Votre réponse est partiellement correcte.
Vous en avez sélectionné correctement 2.
Les réponses correctes sont :
Word2vec,
Skip-gram,
GloVe
Question 13
Correct
Note de 1,00 sur 1,00
Join the type of the gate and where it is used.
Update gate Γu : How much past should matter now?
Forget gate Γ :Erase a cell or not?
f
Relevance gate Γ :Drop previous information?
r
Output gate Γ : How much to reveal of a cell?
o
Votre réponse est correcte.
La réponse correcte est :
Update gate Γu : How much past should matter now? → GRU, LSTM,
Forget gate Γ :Erase a cell or not? → LSTM,
f
Relevance gate Γ :Drop previous information? → GRU, LSTM,
r
Output gate Γ : How much to reveal of a cell?
o
→ LSTM
Question 14
Correct
Note de 1,00 sur 1,00
Gated Recurrent Unit (GRU) are generalization of Long Short-Term Memory units (LSTM)
with combination of the forget and input gates into a single “update gate.”
A. False
B. True
Votre réponse est correcte.
La réponse correcte est :
False
GRU, LSTMLSTMGRU, LSTMLSTMQuestion 15
Correct
Note de 1,00 sur 1,00
Sort the LSTM process in the right order.
The putput gate decides what we’re going to output.
The input gate and the update gate decide what new information we’re going to store in the
cell state
The forget gate decides what information we’re going to throw away from the cell state.
Votre réponse est correcte.
La réponse correcte est :
The putput gate decides what we’re going to output. → 3,
The input gate and the update gate decide what new information we’re going to store in the cell state → 2,
The forget gate decides what information we’re going to throw away from the cell state. → 1
Question 16
Correct
Note de 1,00 sur 1,00
What is the purpose of training RNN model?
A. Learn patterns in ABC music and generate a new piece based on model.
B. Predict following character in each time step
C. Given character & sequence whats the most probable next character
D. Generate a new piece of music based on model
E. Maintaining internal state that depends on previously seen elements
Votre réponse est correcte.
Publicité
La réponse correcte est :
Learn patterns in ABC music and generate a new piece based on model.
321Question 17
Correct
Note de 1,00 sur 1,00
The forget gate looks at h and x , and outputs a number between 0 and 1 for each number in the
t−1
t
cell state C . A 1 represents “completely keep this” while a 0 represents “completely get rid of this.”
t−1
It is helpful to use tanh activation then sigmoid.
A. False
B. True
Votre réponse est correcte.
La réponse correcte est :
False
Question 18
Correct
Note de 1,00 sur 1,00
The GRU combines the gating functions of the input gate and the forget gate into a simple update gate.
Further, the cell state and the hidden output are combined into a single hidden state layer. Choose the
right answer.
A. LSTM trains a little faster than the GRU.
B. GRU trains a little faster than the LSTM.
Votre réponse est correcte.
La réponse correcte est :
GRU trains a little faster than the LSTM.
Question 19
Correct
Note de 1,00 sur 1,00
The gradient clipping (Coupure de gradient) is:
a. a technique used to cope with the vanishing gradient problem sometimes encountered when
performing backpropagation
b. a technique used to cope with the exploding gradient problem sometimes encountered when
performing backpropagation
Votre réponse est correcte.
La réponse correcte est :
a technique used to cope with the exploding gradient problem sometimes encountered when performing
backpropagation
Question 20
Correct
Note de 1,00 sur 1,00
Match the description to thier situation
Happens rarely, but the eect can be catastrophic and might destroy what has been
learned so far.
Means that learning long term dependencies in data is dicult for simple RNN
architecture
The gradients start to increase exponentially during backpropagation through the
recurrent weights
As we propagate the gradients back in time, usually their magnitude quickly
decreases
Votre réponse est correcte.
La réponse correcte est :
Happens rarely, but the eect can be catastrophic and might destroy what has been learned so far.
→ Exploiding gradients,
Means that learning long term dependencies in data is dicult for simple RNN architecture
→ Vanishing gradients,
The gradients start to increase exponentially during backpropagation through the recurrent weights
→ Exploiding gradients,
As we propagate the gradients back in time, usually their magnitude quickly decreases → Vanishing gradients
◄ Test Evaluation #3
Aller à…
Devoir Surveillé 23/12/2021 ►
Exploiding gradientsVanishing gradientsExploiding gradientsVanishing gradients