Deleting a Project

Deleting a Project


A project in Skyl can be deleted by a Project Lead or Business Owner. Once the project has been deleted, the datasets, trained models, and model deployment associated with the project will no longer be accessible.

To delete a project:

  1. Click on “Admin” on sidebar navigation


  2. Select the “Project Settings” tab

  3. Click on the “Delete” button


  4. Click on “Delete Project” in the confirmation popup window.




Machine Learning Definitions

Machine Learning Definitions


What is Machine Learning?

Machine learning sits under the umbrella term, artificial intelligence.  Artificial intelligence is a branch of computer science that deals with how computers learn to mimic human behavior.  Machine learning is a branch of artificial intelligence that studies theability of a computer to continuously train itself through new data inputs.


Manage User Profile

Manage User Profile


Your user profile lists your full name, email, and projects that you are a member of.

To view and update your user profile:

  1. Select the icon containing your initials on the top right-hand corner of the screen

  2. Select “Profile” from the following dropdown menu


From here you can:

  1. View and edit your full name

  2. View your email ID

  3. Change your account password


To update your password:

  1. Select ’Change Password’

  2. Enter your current password

  3. Enter a new password

  4. Select “Save” to change your account password

  5. Select “Cancel” to cancel your password change


Your personal details can be viewed or edited from the admin module as well.

To edit your personal details:

  1. Select the pencil icon after hovering over the Personal Details section
    >


  2. On the right-hand slider, you can edit your

    1. Name
    2. Role
  3. After editing, select “Save”



Manage Team Members

Manage Team Members


Team Members can help you lead a project or label datasets. Team members can be added, removed, and activated or deactivated at any time. An activated team member will can view a project, and a deactivated team member cannot.

To view and manage your team members:

  1. Select “Team Members” on the Welcome page. You will be sent to a list of team members, your shared organizations, and their most recent activity


  2. Activate or deactivate team members by selecting the toggle button

  3. Team members can be activated or deactivated during any point in the process

To invite new team members :

  1. Select “Team Members” on the Welcome Page


  2. On the following page, select “Add New Team Members” on the upper right-hand side

  3. Enter the Name and Email of the new member and select “Add Team Member”


  4. If the user is already a Skyl member, they will receive a notification saying they have been added to this group

  5. If the user is not a Skyl member, they will receive a sign-up request via email




Manage Organisation

Manage Organisation


In Skyl, an organization is a group of users who collaborate on a machine learning project.  Every Skyl user can be a part of multiple organizations.

To view all the organization:

  1. Select the icon containing your initials on the top right corner of your screen

  2. In the dropdown menu, view your organizations and your role


To view or edit your organizational details:

  1. Select Admin from the left dashboard

  2. From here, select the “General” tab

  3. Here, view your personal, organizational, and project details


  4. To edit your organizational details, hover over the Organization Details section and select the pencil icon


  5. On this page, you can edit your:

    1. Organization Name
    2. Organization Address
    3. Country
    4. Email
    5. Mobile Phone
    6. Office Phone
  6. Select the “Save” button when you have finished editing your organization details




Model Deployment

Model Deployment


Deploying machine learning models is the process of putting models into production and sending them to other business systems. Model deployment allows other systems to send in data to receive predictions.  These predictions are then returned to the company systems. Through deployment, you and your business can take full advantage of the model you built. Successful model training delivers a hosted model that is used for predictions.

To deploy your model:

  1. Select “Model Deployment” under Machine Learning. Your list of successfully trained models will appear


  2. Click on ‘Deploy’ button under ‘Deployment’ tab


Configure your model according to your requirements.

Parameter Comment
model_definition_id The architecture id of the model which is dependent upon the kind of ML problem you are trying to solve. Allowed values are image_classification_sc_cnn, image_classification_sc_cnn_resnet, text_extraction_lstm_crf_tfhub, text_classification_sc_usel
auto_batch_size The number of training examples utilized in one iteration.
no_of_epochs An epoch is a full iteration over the training data.
learning_rate Learning rate controls how quickly or slowly a model learns a problem. It is a very small number, usually something like 0.001, that we multiply the gradients by to scale them.
layers.size A layer is a container that usually receives weighted input, transforms it with a set of functions and then passes these values as output to the next layer.
layers.activation_function An activation function takes in weighted data (matrix multiplication between input data and weights) and outputs a non-linear transformation of the data.
optimizer Optimizers shape and mould your model into its most accurate possible form by futzing with the weights.
loss_function It’s a method of evaluating how well your algorithm models your dataset. A smaller value generally indicates a successful model which understands your data well.
metrics Evaluating criteria to define your model’s success like accuracy, loss etc.


Model Training

Model Training


ML model training matches an ML algorithm with selected featureset training data in order to learn. The process of learning involves finding patterns in the training data that map the input data attributes to the target, or, the value that you want to predict.  A successfully trained ML model captures these patterns. Once it does, it can be deployed to perform predictions.

To start your model training:

  1. Select “Training” under Machine Learning


  2. You will be directed to a list of all your completed and ongoing training jobs


  3. On the top right corner, select “Train a New Model”


  4. Fill in the name and description of your ML model


  5. Select the appropriate featureset from the drop-down menu


Configure your model according to your requirements.

Parameter Comment
model_definition_id The architecture id of the model which is dependent upon the kind of ML problem you are trying to solve. Allowed values are image_classification_sc_cnn, image_classification_sc_cnn_resnet, text_extraction_lstm_crf_tfhub, text_classification_sc_usel
auto_batch_size The number of training examples utilized in one iteration.
no_of_epochs An epoch is a full iteration over the training data.
learning_rate Learning rate controls how quickly or slowly a model learns a problem. It is a very small number, usually something like 0.001, that we multiply the gradients by to scale them.
layers.size A layer is a container that usually receives weighted input, transforms it with a set of functions and then passes these values as output to the next layer.
layers.activation_function An activation function takes in weighted data (matrix multiplication between input data and weights) and outputs a non-linear transformation of the data.
optimizer Optimizers shape and mould your model into its most accurate possible form by futzing with the weights.
loss_function It’s a method of evaluating how well your algorithm models your dataset. A smaller value generally indicates a successful model which understands your data well.
metrics Evaluating criteria to define your model’s success like accuracy, loss etc.


Featureset

Featureset


A featureset is either a collection of data or a subset of the dataset.  The featureset is the set of data which eventually becomes the input for your model training. Feature Selection is an important step in the machine learning pipeline because it has the most impact on your prediction variable or output.

To create a featureset in Skyl:

  1. Select Machine Learning from the left menu


  2. Click on “Feature Set” to be directed to all previously created featuresets


  3. On the top right corner, select “Add Featureset”


  4. Fill in the name and description of the dataset


  5. From the drop-down menu, select the dataset from which the featureset will be selected


  6. On the bottom tab labeled “Feature Selection”, select the policy that will train the dataset. A policy can either extract explicitly from the dataset or split the dataset.


  7. Select the input and output features from the listed columns to configure the featureset according to your requirements


Please note that the output features are the value(s) which you want to predict using your model.

A policy defines how to select your featureset from the dataset.  You can either extract explicitly from the dataset or split the dataset.



Inviting a Project lead

Inviting a Project lead


A project lead can add or remove users from a project, activate or deactivate user accounts, and collaborate on a project.

  1. To invite a project lead, select the “Team Members” tab on the welcome page to your list of team members.

  2. From here, click “Invite Team Member” on the upper-right hand side of the page

  3. Once you invite a team member, fill in their name, email, and role

  4. Click “Invite Team Member” to invite the new project lead, or “Cancel” if you do not need a new team member



Selecting a Machine Learning Template

Selecting a Machine Learning Template


A machine learning template is a guided workflow that creates ML projects seamlessly. They simplify the ML process by allowing you to streamline your project depending upon your use-case.

You can choose between image classification, text classification, and natural language extraction templates. Respectfully, these templates help categorize images, classify text, and extract keywords from text.

ML templates customise options for data collection, data labelling, and even algorithms for machine learning depending on the use-case and suggestions.

  1. Select the "Add Project" box

  2. You will be directed to a templates page

  3. Choose between Computer Vision projects and Natural Language Processing projects

    1. Under Computer Vision, you can either choose Single Class or Multi Class image classification projects
    2. Under Natural Language Processing you can choose between Text Extraction, Text Classification, or Multi Label Classification projects
  4. After selecting your template, you will be able to name, describe, and add members to your project