Chapter 10: Summary added #57
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
martinacantaro
requested changes
Mar 17, 2021
10_bees_vs_wasps/10_bees_vs_wasps.jl
Outdated
| ### Summary | ||
| In this chapter, we implemented a convolutional neural network that discriminated between pictures of bees and wasps. | ||
| First, we saw how neural networks work and explained their training process, where we set a loss function that indicates how our model is performing and feed it with labeled data so that their parameters find the right setting to optimize the loss function. |
Collaborator
There was a problem hiding this comment.
replace: indicates
by: evaluates
Collaborator
There was a problem hiding this comment.
I think the clarity of this line can be improved. Maybe break it into two sentences, with a clear definition of loss function
10_bees_vs_wasps/10_bees_vs_wasps.jl
Outdated
| In this chapter, we implemented a convolutional neural network that discriminated between pictures of bees and wasps. | ||
| First, we saw how neural networks work and explained their training process, where we set a loss function that indicates how our model is performing and feed it with labeled data so that their parameters find the right setting to optimize the loss function. | ||
| Then we explained that convolutional neural networks are a particular kind of neural networks with the characteristic that their layers contain filters and have a great performance working with images. |
Collaborator
There was a problem hiding this comment.
We learned that convolutional neural networks are a particular kind of neural networks where layers act as filters, and that they have have a great performance when working with images.
10_bees_vs_wasps/10_bees_vs_wasps.jl
Outdated
| First, we saw how neural networks work and explained their training process, where we set a loss function that indicates how our model is performing and feed it with labeled data so that their parameters find the right setting to optimize the loss function. | ||
| Then we explained that convolutional neural networks are a particular kind of neural networks with the characteristic that their layers contain filters and have a great performance working with images. | ||
| Thus, we decided to create a simple convolutional neural network to classify the bees and wasps pictures. |
Collaborator
There was a problem hiding this comment.
to classify our pictures of bees and wasps.
10_bees_vs_wasps/10_bees_vs_wasps.jl
Outdated
| Thus, we decided to create a simple convolutional neural network to classify the bees and wasps pictures. | ||
| We pre-processed our data, converting all images to gray scale and changing their resolution to keep the convolutional neural networks as simple as possible. | ||
| To train the neural networks in an efficient way we divided the data in small batches and passed forward to the model in small groups. |
Collaborator
There was a problem hiding this comment.
we divided the data in small batches which we fed to the model one by one.
10_bees_vs_wasps/10_bees_vs_wasps.jl
Outdated
| Thus, we decided to create a simple convolutional neural network to classify the bees and wasps pictures. | ||
| We pre-processed our data, converting all images to gray scale and changing their resolution to keep the convolutional neural networks as simple as possible. | ||
| To train the neural networks in an efficient way we divided the data in small batches and passed forward to the model in small groups. | ||
| Then we plotted the accuracy and loss function of our model to see how it performed. |
Collaborator
There was a problem hiding this comment.
to see how well it performed.
10_bees_vs_wasps/10_bees_vs_wasps.jl
Outdated
| We pre-processed our data, converting all images to gray scale and changing their resolution to keep the convolutional neural networks as simple as possible. | ||
| To train the neural networks in an efficient way we divided the data in small batches and passed forward to the model in small groups. | ||
| Then we plotted the accuracy and loss function of our model to see how it performed. | ||
| Finally, we tried to improve our model, so we decreased the learning rate and trained again our model, obtaining better accuracy. |
Collaborator
There was a problem hiding this comment.
, so we decreased the learning rate and trained it again,
…eedback-to-do-messages Chapter 10: Added feedback and to do messages
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR just modifies the Pluto file. The
.htmland.rmdfiles modifications are already merged in master