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 7560815054092

Tags

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

Question

The internal state in LSTM layers is also accumulated when evaluating a network and when making predictions. Therefore, if you are using a [...] LSTM, you must reset state after evaluating the network on a validation dataset or after making predictions

Answer

stateful

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 internal state in LSTM layers is also accumulated when evaluating a network and when making predictions. Therefore, if you are using a stateful LSTM, you must reset state after evaluating the network on a validation dataset or after making predictions

Original toplevel document (pdf)

cannot see any pdfs

Annotation 7560817937676

#feature-engineering #lstm #recurrent-neural-networks #rnn

HMM == Hidden Markov Model

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

Parent (intermediate) annotation

Open it
The HMM has N discrete hidden states (where N is typically small) and, therefore, has only log 2 (N) bits of information available to capture the sequence history (Brown & Hinton, 2001). On

Original toplevel document (pdf)

cannot see any pdfs

Flashcard 7560820296972

Tags

#feature-engineering #lstm #recurrent-neural-networks #rnn

Question

HMM == [...] Markov Model

Answer

Hidden

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
HMM == Hidden Markov Model

Original toplevel document (pdf)

cannot see any pdfs

Flashcard 7560822131980

Tags

#feature-engineering #lstm #recurrent-neural-networks #rnn

Question

Demand forecasting for products within a category is a critical task for retailers and brand managers alike. The [...] logit model (MNL) is commonly used to predict brand choice and market share using marketing-mix and loyalty variables (Guadagni & Little, 1983)

Answer

multinomial

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
Demand forecasting for products within a category is a critical task for retailers and brand managers alike. The multinomial logit model (MNL) is commonly used to predict brand choice and market share using marketing-mix and loyalty variables (Guadagni & Little, 1983)

Original toplevel document (pdf)

cannot see any pdfs

Flashcard 7560823966988

Tags

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

Question

The choice of [...] is most important for the output layer as it will define the format that predictions will take.

Answer

activation function

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 choice of activation function is most important for the output layer as it will define the format that predictions will take.

Original toplevel document (pdf)

cannot see any pdfs

Flashcard 7560825801996

Tags

#feature-engineering #lstm #recurrent-neural-networks #rnn

Question

[...] models in direct marketing predict customer responses from past customer behavior and marketing activity. These models often summarize past events using features such as recency or frequency and the process of feature engineering has received significant attention

Answer

Response

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
Response models in direct marketing predict customer responses from past customer behavior and marketing activity. These models often summarize past events using features such as recency or freq

Original toplevel document (pdf)

cannot see any pdfs

Flashcard 7560827637004

Tags

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

Question

For a [...] classification problem, the results may be in the form of an array of probabilities (assuming a one hot encoded output variable) that may need to be converted to a single class output prediction using the argmax() NumPy function.

Answer

multiclass

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
For a multiclass classification problem, the results may be in the form of an array of probabilities (assuming a one hot encoded output variable) that may need to be converted to a single class output p

Original toplevel document (pdf)

cannot see any pdfs

Flashcard 7560829734156

Tags

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

[unknown IMAGE 7104054824204]

Question

You can specify the input shape argument that expects a tuple containing the number of [...] and the number of features

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
You can specify the input shape argument that expects a tuple containing the number of time steps and the number of features

Original toplevel document (pdf)

cannot see any pdfs

Annotation 7560831831308

#feature-engineering #lstm #recurrent-neural-networks #rnn

Since customer transactions occur sequentially, they can be modeled as a sequence prediction task using an RNN as well, where all firm actions and customer responses are represented by elements in a vector.

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

Parent (intermediate) annotation

Open it
The RNN processes the entire sequence of available data without having to summarize it into features. Since customer transactions occur sequentially, they can be modeled as a sequence prediction task using an RNN as well, where all firm actions and customer responses are represented by elements in a vector. For instance, suppose a firm solicits customers either through phone, mail, or email (three channels), and custo mers may purchase across 17 product categories. All the analyst has to d

Original toplevel document (pdf)

cannot see any pdfs

Flashcard 7560833666316

Tags

#feature-engineering #lstm #recurrent-neural-networks #rnn

Question

The RNN processes the [...] sequence of available data without having to summarize it into features.

Answer

entire

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 RNN processes the entire sequence of available data without having to summarize it into features.

Original toplevel document (pdf)

cannot see any pdfs

Annotation 7560835763468

#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data

Consumer behavior is inherently sequential which makes RNNs a perfect fit

status	not read	reprioritisations
last reprioritisation on		suggested re-reading day
started reading on		finished reading on

Parent (intermediate) annotation

Open it
Consumer behavior is inherently sequential which makes RNNs a perfect fit. We are employing RNNs in production now which offers significant advantages over existing methods: reduced feature engineering; improved empirical performance; and better prediction ex

Original toplevel document (pdf)

cannot see any pdfs

Flashcard 7560838647052

Question

[...]: radar plots with ggplot in R

Answer

ggradar

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

Open it
ggradar: radar plots with ggplot in R

Flashcard 7560840482060

Tags

#English #vocabulary

Question

arduous

/ˈɑːdjʊəs,ˈɑːdʒʊəs/

Learn to pronounce

adjective

involving or requiring strenuous effort; difficult and [...]

Answer

tiring

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
arduous /ˈɑːdjʊəs,ˈɑːdʒʊəs/ Learn to pronounce adjective involving or requiring strenuous effort; difficult and tiring

Original toplevel document

Open it
arduous /ˈɑːdjʊəs,ˈɑːdʒʊəs/ Learn to pronounce adjective involving or requiring strenuous effort; difficult and tiring "an arduous journey" Similar: onerous taxing difficult hard heavy laborious burdensome

Flashcard 7560842317068

Tags

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

Question

The LSTM expects input data to have the dimensions: [...], time steps, and features.

Answer

samples

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 LSTM expects input data to have the dimensions: samples, time steps, and features.

Original toplevel document (pdf)

cannot see any pdfs

Flashcard 7560844152076

Tags

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

Question

The promise of recurrent neural networks is that the temporal dependence and contextual information in the input data can be learned. A recurrent network whose inputs are not fixed but rather constitute an input sequence can be used to transform an input sequence into an output sequence while taking into account [...] information in a flexible way

Answer

contextual

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
n be learned. A recurrent network whose inputs are not fixed but rather constitute an input sequence can be used to transform an input sequence into an output sequence while taking into account <span>contextual information in a flexible way <span>

Original toplevel document (pdf)

cannot see any pdfs

Flashcard 7560845987084

Tags

#recurrent-neural-networks #rnn

Question

The challenge for deep learning models of customer behavior remains their opaque nature and the lack of simple ways to interpret their behavior, which is especially true for the complex [...] dynamics of RNNs.

Answer

temporal

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 for deep learning models of customer behavior remains their opaque nature and the lack of simple ways to interpret their behavior, which is especially true for the complex temporal dynamics of RNNs. <span>

Original toplevel document (pdf)

cannot see any pdfs

Edited, memorised or added to reading queue

on 02-Feb-2023 (Thu)

Parent (intermediate) annotation

Original toplevel document (pdf)

Parent (intermediate) annotation

Original toplevel document (pdf)

Parent (intermediate) annotation

Original toplevel document (pdf)

Parent (intermediate) annotation

Original toplevel document (pdf)

Parent (intermediate) annotation

Original toplevel document (pdf)

Parent (intermediate) annotation

Original toplevel document (pdf)

Parent (intermediate) annotation

Original toplevel document (pdf)

Parent (intermediate) annotation

Original toplevel document (pdf)

Parent (intermediate) annotation

Original toplevel document (pdf)

Parent (intermediate) annotation

Original toplevel document (pdf)

Parent (intermediate) annotation

Original toplevel document (pdf)

[...]: radar plots with ggplot in R

Parent (intermediate) annotation

Original toplevel document

Parent (intermediate) annotation

Original toplevel document (pdf)

Parent (intermediate) annotation

Original toplevel document (pdf)

Parent (intermediate) annotation

Original toplevel document (pdf)