Podcast
Questions and Answers
Estimating ______ Latency is an important step in optimizing a model.
Estimating ______ Latency is an important step in optimizing a model.
Model
The goal of ______ is to reduce the computational resources required by a model.
The goal of ______ is to reduce the computational resources required by a model.
Quantization
Before optimizing a model, you should first make sure that ______ matters.
Before optimizing a model, you should first make sure that ______ matters.
it
Contributing to ______ source projects can help to improve model efficiency.
Contributing to ______ source projects can help to improve model efficiency.
Signup and view all the answers
The chapter also discusses ______ Cycling as a method to reduce energy usage.
The chapter also discusses ______ Cycling as a method to reduce energy usage.
Signup and view all the answers
To prevent momentary glitches from causing problems, we could take the average of all of our ______ outputs across a period of time.
To prevent momentary glitches from causing problems, we could take the average of all of our ______ outputs across a period of time.
Signup and view all the answers
Real-world ______ is often messy and machine learning models aren’t perfect.
Real-world ______ is often messy and machine learning models aren’t perfect.
Signup and view all the answers
We use this technique to help with wake-word detection in Chapter ______.
We use this technique to help with wake-word detection in Chapter ______.
Signup and view all the answers
This would mean that transient issues are ______, and we only act upon consistent behavior.
This would mean that transient issues are ______, and we only act upon consistent behavior.
Signup and view all the answers
Since real-world ______ is often messy and machine learning models aren’t perfect, it’s possible that a temporary glitch might result in an incorrect classification.
Since real-world ______ is often messy and machine learning models aren’t perfect, it’s possible that a temporary glitch might result in an incorrect classification.
Signup and view all the answers
We could run our ______ on the current data window every 10 seconds, and take the averages of the last 6 outputs.
We could run our ______ on the current data window every 10 seconds, and take the averages of the last 6 outputs.
Signup and view all the answers
To make the most of limited data, a technique called ______ can be used to generate new, artificial datapoints.
To make the most of limited data, a technique called ______ can be used to generate new, artificial datapoints.
Signup and view all the answers
Regularization techniques are used to make deep learning ______ less likely to overfit their training data.
Regularization techniques are used to make deep learning ______ less likely to overfit their training data.
Signup and view all the answers
One regularization technique involves ______ the connections between neurons during training.
One regularization technique involves ______ the connections between neurons during training.
Signup and view all the answers
Data augmentation is a way to artificially expand the size of a ______ dataset.
Data augmentation is a way to artificially expand the size of a ______ dataset.
Signup and view all the answers
Regularization techniques generally involve ______ the model in some way to prevent it from perfectly memorizing the data.
Regularization techniques generally involve ______ the model in some way to prevent it from perfectly memorizing the data.
Signup and view all the answers
The best way to beat overfitting, when possible, is to get your hands on a larger and more ______ dataset.
The best way to beat overfitting, when possible, is to get your hands on a larger and more ______ dataset.
Signup and view all the answers
