Edited, memorised or added to reading queue

on 25-Jun-2024 (Tue)

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

Flashcard 7628365106444

Tags
#deep-learning #keras #lstm #python #sequence
Question
Sequence-to-sequence prediction involves predicting an [...] given an input sequence. For example: Input Sequence: 1, 2, 3, 4, 5 Output Sequence: 6, 7, 8, 9, 1
Answer
output sequence

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
Sequence-to-sequence prediction involves predicting an output sequence given an input sequence. For example: Input Sequence: 1, 2, 3, 4, 5 Output Sequence: 6, 7, 8, 9, 1

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7642235145484

#recurrent-neural-networks #rnn
This paper presents a new approach that helps firms leverage the automatic feature extraction capabilities of a specific type of deep learning models when applied to customer transaction histories in non-contractual business settings (i.e., when the time at which a customer becomes inactive is unobserved by the firm). We show how the proposed deep learning model improves on established models both in terms of individual-level accuracy and overall cohort-level bias. It also helps managers in capturing seasonal trends and other forms of purchase dynamics that are important to detect in a timely manner for the purpose of proactive customer-base management
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
elated context factors to forecast future behavior, and to link these forecasts with actionable characteristics of individuals, managerially significant customer sub-groups, and entire cohorts. <span>This paper presents a new approach that helps firms leverage the automatic feature extraction capabilities of a specific type of deep learning models when applied to customer transaction histories in non-contractual business settings (i.e., when the time at which a customer becomes inactive is unobserved by the firm). We show how the proposed deep learning model improves on established models both in terms of individual-level accuracy and overall cohort-level bias. It also helps managers in capturing seasonal trends and other forms of purchase dynamics that are important to detect in a timely manner for the purpose of proactive customer-base management. We demonstrate the model performance in eight empirical real-life settings which vary broadly in transaction frequency, purchase (ir)regularity, customer attrition, availability of con

Original toplevel document (pdf)

cannot see any pdfs



Annotation 7642236980492

#feature-engineering #lstm #recurrent-neural-networks #rnn
Models with low capacity would underfit the training set and hence have a high bias. However , models with high capacity may overfit the training set and exhibit high variance. Representational capacity is the ability of the model to fit a wide range of functions. However, the effective capacity of a model might be lower than its representational capacity because of limitations and shortcomings, such as imperfect optimization or suboptimal hyperparameters (Goodfellow et al., 2016). To increase the match of the model's effective capacity and the complexity of the task at hand, the analyst needs to tune both the parameters and the hyperparameters of the model.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
the parameters and hyperparameters such that the model reaches optimal capacity (Goodfellow et al., 2016) and therefore maximizes the chances that the model will generalize well to unseen data. <span>Models with low capacity would underfit the training set and hence have a high bias. However , models with high capacity may overfit the training set and exhibit high variance. Representational capacity is the ability of the model to fit a wide range of functions. However, the effective capacity of a model might be lower than its representational capacity because of limitations and shortcomings, such as imperfect optimization or suboptimal hyperparameters (Goodfellow et al., 2016). To increase the match of the model's effective capacity and the complexity of the task at hand, the analyst needs to tune both the parameters and the hyperparameters of the model. Given how sensitive LSTM models are to hyperparameter tuning, this area requires particular attention. <span>

Original toplevel document (pdf)

cannot see any pdfs



Annotation 7642238553356

#feature-engineering #lstm #recurrent-neural-networks #rnn
To increase the match of the model's effective capacity and the complexity of the task at hand, the analyst needs to tune both the parameters and the hyperparameters of the model. Given how sensitive LSTM models are to hyperparameter tuning, this area requires particular attention.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
ity of a model might be lower than its representational capacity because of limitations and shortcomings, such as imperfect optimization or suboptimal hyperparameters (Goodfellow et al., 2016). <span>To increase the match of the model's effective capacity and the complexity of the task at hand, the analyst needs to tune both the parameters and the hyperparameters of the model. Given how sensitive LSTM models are to hyperparameter tuning, this area requires particular attention. <span>

Original toplevel document (pdf)

cannot see any pdfs



Annotation 7642240388364

#ML_in_Action #learning #machine #software-engineering
It, in essence, is the road map to creating ML-based systems that can be not only deployed to production, but also maintained and updated for years in the future, allowing businesses to reap the rewards in efficiency, profitability, and accuracy that ML, in general, has proven to provide (when done correctly)
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
a set of standards, tools, processes, and methodology that aims to minimize the chances of abandoned, misguided, or irrelevant work being done in an effort to solve a business problem or need. <span>It, in essence, is the road map to creating ML-based systems that can be not only deployed to production, but also maintained and updated for years in the future, allowing businesses to reap the rewards in efficiency, profitability, and accuracy that ML, in general, has proven to provide (when done correctly). <span>

Original toplevel document (pdf)

cannot see any pdfs



Annotation 7642242223372

#deep-learning #keras #lstm #python #sequence
Think of the internal state of LSTMs as a handy internal variable to capture and provide context for making predictions. If your problem looks like a traditional autoregression type problem with the most relevant lag observations within a small window, then perhaps develop a baseline of performance with an MLP and sliding window before considering an LSTM.
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
The caution is that LSTMs are not a silver bullet and to carefully consider the framing of your problem. Think of the internal state of LSTMs as a handy internal variable to capture and provide context for making predictions. If your problem looks like a traditional autoregression type problem with the most relevant lag observations within a small window, then perhaps develop a baseline of performance with an MLP and sliding window before considering an LSTM.

Original toplevel document (pdf)

cannot see any pdfs