Edited, memorised or added to reading queue

on 15-Nov-2024 (Fri)

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

Flashcard 7666639703308

Tags
#feature-engineering #lstm #recurrent-neural-networks #rnn
Question
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 [...] LSTM models are to hyperparameter tuning, this area requires particular attention.
Answer
sensitive

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
an> 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 <span>sensitive LSTM models are to hyperparameter tuning, this area requires particular attention. <span>

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7666641538316

#feature-engineering #lstm #recurrent-neural-networks #rnn
Models with low capacity would underfit the training set and hence have a high bias
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
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. Howe

Original toplevel document (pdf)

cannot see any pdfs



Annotation 7666643111180

#feature-engineering #lstm #recurrent-neural-networks #rnn
models with high capacity may overfit the training set and exhibit high variance
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
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 bec

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7666644946188

Tags
#deep-learning #keras #lstm #python #sequence
Question
You can [...] your dataset using the scikit-learn object MinMaxScaler
Answer
normalize

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
You can normalize your dataset using the scikit-learn object MinMaxScaler

Original toplevel document (pdf)

cannot see any pdfs






Annotation 7666646781196

#feature-engineering #lstm #recurrent-neural-networks #rnn
For natural language processing, an RNN would encode the sentence “A black cat jumped on the table” as a sequence of seven vectors (x 1 , x 2 , … x 7 ), where each word would be represented as a single non-zero value in a sparse vector
statusnot read reprioritisations
last reprioritisation on suggested re-reading day
started reading on finished reading on


Parent (intermediate) annotation

Open it
For natural language processing, an RNN would encode the sentence “A black cat jumped on the table” as a sequence of seven vectors (x 1 , x 2 , … x 7 ), where each word would be represented as a single non-zero value in a sparse vector 2 (Goodfellow et al., 2016). For instance, if we train a model with a vocabulary of 100,000 words, the first word “A” in the sentence would be encoded as a sparse vector of 100,000 nume

Original toplevel document (pdf)

cannot see any pdfs



Flashcard 7666649140492

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

We can summarize the 3 key benefits of LSTMs as:

2. Possesses [...] to overcome the issues of long-term temporal dependency with input sequences

Answer
memory

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
We can summarize the 3 key benefits of LSTMs as: 2. Possesses memory to overcome the issues of long-term temporal dependency with input sequences

Original toplevel document (pdf)

cannot see any pdfs






Flashcard 7666650975500

Question

To create an environment with a specific version of Python and multiple packages including a package with a specific version:

$ conda create -n <env_name> python=<version#> <packagename> <packagename> <packagename>[...]
Answer
=<version#>

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
f Python and multiple packages including a package with a specific version: $ conda create -n <env_name> python=<version#> <packagename> <packagename> <packagename><span>=<version#> <span>

Original toplevel document

How to Manage Python Dependencies with Conda - ActiveState
rmine the Current Environment with Conda The current or active environment is shown in parentheses () or brackets [] at the beginning of the Anaconda Prompt or terminal: (<current_env>) $ <span>Recommendations for Avoiding Dependency Conflicts with Conda There are two simple rules to follow: Always create a new environment for each project Install all the packages that you need in the new environment at the same time. Installing packages one at a time can lead to dependency conflicts. To create an environment with a specific version of Python and multiple packages including a package with a specific version: $ conda create -n <env_name> python=<version#> <packagename> <packagename> <packagename>=<version#> Alternatively, you can use conda to install all the packages in a requirements.txt file. You can save a requirements.txt file from an existing environment, or manually create a new requirements.txt for a different environment. To create a conda requirements.txt file from an existing environment: Activate your project environment. See section above entitled “How to Activate an Environment with Conda” for detai