Edited, memorised or added to reading queue

on 26-Oct-2024 (Sat)

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

Annotation 7103807622412

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

Limitations of using MLP for sequence predicting

This can work well on some problems, but it has 5 critical limitations.

Stateless .

MLPs learn a fixed function approximation. Any outputs that are conditional on the context of the input sequence must be generalized and frozen into the network weights.

Unaware of Temporal Structure.

Time steps are modelled as input features, meaning that the network has no explicit handling or understanding of the temporal structure or order between observations.

Messy Scaling .

For problems that require modeling multiple parallel input sequences, the number of input features increases as a factor of the size of the sliding window without any explicit separation of time steps of series.

Fixed Sized Inputs

The size of the sliding window is fixed and must be imposed on all inputs to the network.

Fixed Sized Outputs .

The size of the output is also fixed and any outputs that do not conform must be forced. MLPs do offer great capability for sequence prediction but still suffer from this key limitation of having to specify the scope of temporal dependence between observations explicitly upfront in the design of the model.

Sequences pose a challenge for [deep neural networks] because they require that the dimensionality of the inputs and outputs is known and fixed. — Sequence to Sequence Learning with Neural Networks, 2014 MLPs are a good starting point for modeling sequence prediction problems, but we now have better options.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on

pdf

cannot see any pdfs



Flashcard 7662980959500

Tags
#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data
Question
feature engineering: a fixed set of identifiers f i has to be designed to capture the essence of an individual consumer history. Only signals that are [...] in the feature vector can be picked up by the prediction model. Defining expressive features often requires both, domain knowledge as well as data-science intuition
Answer
encoded

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
feature engineering: a fixed set of identifiers f i has to be designed to capture the essence of an individual consumer history. Only signals that are encoded in the feature vector can be picked up by the prediction model. Defining expressive features often requires both, domain knowledge as well as data-science intuition

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7662983318796

Tags
#RNN #ariadne #behaviour #consumer #deep-learning #priority #recurrent-neural-networks #retail #simulation #synthetic-data
Question
While preprocessing is an important tool to improve model performance, it artificially increases the dimensionality of the input vector. Also, the resulting binary features can be strongly correlated. Both outcomes make it difficult to tell which [...] in the underlying consumer histories have a strong impact on the prediction outcome
Answer
action patterns

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
odel performance, it artificially increases the dimensionality of the input vector. Also, the resulting binary features can be strongly correlated. Both outcomes make it difficult to tell which <span>action patterns in the underlying consumer histories have a strong impact on the prediction outcome <span>

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7662985153804

#feature-engineering #lstm #recurrent-neural-networks #rnn
The effect of a direct mailing does not end after the campaign is over, and the customer has made her decision to respond or not.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
The effect of a direct mailing does not end after the campaign is over, and the customer has made her decision to respond or not. An advertising campaign or customer retention program can impact customers' behaviors for several weeks, even months. Customers tend to remember past events, at least partially. Hence,

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7662986988812

Tags
#feature-engineering #lstm #recurrent-neural-networks #rnn
Question
The LSTM network forms a chain of repeating modules, like any RNN, but the modules, apart from the external recurrent function of the RNN, possess an internal recurrence (or [...]), which lets the gradients flow for long durations without exploding or vanishing
Answer
self-loop

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
The LSTM network forms a chain of repeating modules, like any RNN, but the modules, apart from the external recurrent function of the RNN, possess an internal recurrence (or self-loop), which lets the gradients flow for long durations without exploding or vanishing

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7662989872396

Tags
#recurrent-neural-networks #rnn
Question
In this paper, we offer marketing analysts an alternative to these models by developing a deep learning based approach that does not rely on any ex-ante data labelling or feature engineering, but instead automatically detects behavioral dynamics like seasonality or changes in [...] timing patterns by learning directly from the prior transaction history
Answer
inter-event

statusnot learnedmeasured difficulty37% [default]last interval [days]               
repetition number in this series0memorised on               scheduled repetition               
scheduled repetition interval               last repetition or drill

Parent (intermediate) annotation

Open it
ping a deep learning based approach that does not rely on any ex-ante data labelling or feature engineering, but instead automatically detects behavioral dynamics like seasonality or changes in <span>inter-event timing patterns by learning directly from the prior transaction history <span>

Original toplevel document (pdf)

cannot see any pdfs