artificialintelligencetoolkit / aitk Goto Github PK

Install must be added for TrainFollow notebook in order to run on Google Colab.

%pip install aitk --quiet

For more comments see Google Colab TrainFollow Notebook.

Install must be added for XOR notebook in order to run on Google Colab.

%pip install aitk --quiet

Change line 2 to :

import aitk.networks 
#aitk.networks.__version__

Additionally the block of code in line 16 has some issues which I was not able to fix:

for epoch, weights in net.get_weights_from_history():
    net.set_weights(weights)
    net.predict_pca(inputs, scale=.5, colors=["r", "b", "b", "r"], sizes=300)
    input("Epoch %s" % epoch)

For more comments see Google Colab XOR Notebook.

In a notebook cell, I ran

world.watch()

When I ran this on my macbook, the cell outputted this text:

Image(value=b'\xff\xd8\xff\xe0\x00\x10JFIF\x00\x01\x01\x00\x00\x01\x00\x01\x00\x00\xff\xdb\x00C\x00\x08\x06\x0…

When I run this in CoLab, the image of the world renders, and updates, correctly. However, when I press "Mirror output in tab" to show that cell in a side window (so that it keeps showing as I scroll through the notebook), the cell in that side window also outputs the above text.

I expected the image to render in all three contexts.

I tried the following:

x = range(1, 3)

And got this error:

ERROR:

I expected to see blah blah blah. This is the text

Install must be added for CollectReinforcementData notebook in order to run on Google Colab.

%pip install aitk --quiet

For more comments see Google Colab CollectReinforcementData Notebook.

A single neuron with at least 3 inputs and a bias. The user should be able to specify the inputs, the weights, and the activation function. Once these are specified the activation value of the neuron is displayed.

Two installs must be added for Structure_of_Convolutional_Neural_Networks notebook in order to run on Google Colab.

%pip install aitk --quiet

AND

%pip install tf --quiet

For more comments see Google Colab Structure_of_Convolutional_Neural_Networks Notebook.

Install must be added for Coverage notebook in order to run on Google Colab.

%pip install aitk --quiet

For more comments see Google Colab Coverage Notebook.

The install must be added:

%pip install aitk --quiet

In addition to the problem with the install, the LightEnclosed world is once again not able to load, so the rest of the notebook breaks. This occurs in line 9.

world = aitk.robots.load_world("LightEnclosed")

For more comments see: Google Colab Subsumption notebook.

There seems to be an import based error with this code on line 34:

network = create_network(robot)

This code not running breaks the entire rest of the notebook essentially.
Google Colab Robot_Memory

Install must be added for ZigZagWall notebook in order to run on Google Colab.

%pip install aitk --quiet

For more comments see Google Colab ZigZagWall Notebook.

Added:

%pip install aitk --quiet

Changed code block three from:

(x_train, y_train), (x_test, y_test) = await mnist.load_data_async()

To:

(x_train, y_train), (x_test, y_test) =  mnist.load_data()

For additional comments see Google Colab AITKKeras

Install must be added for CartWorld notebook in order to run on Google Colab.

%pip install aitk --quiet

For more comments see Google Colab CartWorld Notebook.

In this notebook, we will provide an accessible example to biased datasets in neural networks. This smaller example will provide a conduit to explaining larger issues with bias in the training of neural networks.

Possible datasets:

1. Only using two words: 0 and 1
2. Using TinyStories: https://arxiv.org/abs/2305.07759
   a. Dataset: https://huggingface.co/datasets/roneneldan/TinyStories

Possible models:

1. Not sure

The world "LightEnclosed" is not recognized in line 4 of the SeekLight notebook.

world = aitk.robots.load_world("LightEnclosed")

Fore more comments see: Google Colab SeekLight notebook

Once again having an issues with the input dataset as in the ClassifyingDigits notebook.

In line 3:
Code:

inputs = get_digit_inputs()

Throws this error:

FileNotFoundError                         Traceback (most recent call last)

<ipython-input-3-73e7cc90aa80> in <cell line: 1>()
----> 1 inputs = get_digit_inputs()
      2 inputs.shape

<ipython-input-2-cdd8a157308e> in get_digit_inputs()
      1 def get_digit_inputs():
      2     """Each digit is represented by a 6x6 grid of 1's and 0's separated by blank lines."""
----> 3     fp = open("digits.data", "r")
      4     data = []
      5     while True:

FileNotFoundError: [Errno 2] No such file or directory: 'digits.data'

This then breaks the code further down when trying to access the input dataset. Further, an install statement must be added before neural networks are used.

For more comments regarding this notebook see: Google Colab ClassifyDigitsWithPCA notebook

Install must be added for CollectData notebook in order to run on Google Colab.

%pip install aitk --quiet

For more comments see Google Colab CollectData Notebook.

Install must be added for MazeSearch notebook in order to run on Google Colab.

%pip install aitk --quiet

For more comments see Google Colab MazeSearch Notebook.

Even after adding an install for aitk, the notebook's file 'follow_data.csv' does not appear to be accessible, making this code in line 2 unable to run.

df = pd.read_csv('follow_data.csv', sep=',')

For more comments, see Google Colab BalanceData.

Having an error in line 3:

Code:

inputs = get_digit_inputs()

Error:

---------------------------------------------------------------------------

FileNotFoundError                         Traceback (most recent call last)

[<ipython-input-4-73e7cc90aa80>](https://localhost:8080/#) in <cell line: 1>()
----> 1 inputs = get_digit_inputs()
      2 inputs.shape

[<ipython-input-1-cdd8a157308e>](https://localhost:8080/#) in get_digit_inputs()
      1 def get_digit_inputs():
      2     """Each digit is represented by a 6x6 grid of 1's and 0's separated by blank lines."""
----> 3     fp = open("digits.data", "r")
      4     data = []
      5     while True:

FileNotFoundError: [Errno 2] No such file or directory: 'digits.data'

After adding import statement, some of the code begins to work. However, since the inputs has not been given a dataset, the network is not able to be trained, and this breaks the rest of the notebook.

For more comments on this notebook see: Google Colab ClassifyingDigits.

Install must be added for CompassAndBeacon notebook in order to run on Google Colab.

%pip install aitk --quiet

For more comments see [Google Colab CompassAndBeacon Notebook](https://colab.research.google.com/drive/1rVHpN1V6zU6XSCOEZMu6NTDwR31_wqOw?usp=drive_link.

Install must be added for StringGA notebook in order to run on Google Colab.

%pip install aitk --quiet

For more comments see Google Colab StringGA Notebook.