concept output in category AI

appears as: n output, output, outputs, The output, outputs, output
Interpretable AI MEAP V03

This is an excerpt from Manning's book Interpretable AI MEAP V03.

Supervised Learning is a type of machine learning system where the objective is to learn a mapping from an input to an output based on example input-output pairs. It requires labeled training data where inputs (also known as features) have a corresponding label (also known as target). Now how is this data represented? The input features are typically represented using a multi-dimensional array data structure or mathematically as a matrix X. The output or target is represented as a single-dimensional array data structure or mathematically as a vector y. The dimension of matrix X is typically m x n, where m represents the number of examples or labeled data and n represents the number of features. The dimension of vector y is typically m x 1 where m again represents the number of examples or labels. The objective is to learn a function f that maps from input features X to the target y. This is shown in Figure 1.5.

Figure 1.5: Illustration of Supervised Learning
A screenshot of a cell phone Description automatically generated

In Figure 1.5 you can see how with supervised learning you are learning a function f that takes in multiple input features represented as X and provides an output that matches known labels or values represented as the target variable y. The bottom half of the figure shown an example where a labeled dataset is given and through supervised learning, you are learning how to map the input features to the output. The function f is a multivariate function since it maps from multiple input variables or features to a target. There are two broad classes of supervised learning problems:

  • The machine learning process is straightforward to understand, and you can clearly interpret how the input features get transformed into the output or target variable.
  • # Hyper parameters
    num_epochs = 5
    learning_rate = 0.002
     
    # Criterion or loss function 
    criterion = nn.CrossEntropyLoss()
     
    # Optimizer for CNN
    optimizer = torch.optim.Adamax(model.parameters(), lr=learning_rate)
     
    for epoch in range(num_epochs):
    model.train()
     
    for idx, (inputs, labels) in enumerate(loader_train):
                inputs = inputs.to(device, dtype=torch.float)
                labels = labels.to(device, dtype=torch.long)
                
                # zero the parameter gradients
                optimizer.zero_grad()
                
                with torch.set_grad_enabled(True):
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1)
                    loss = criterion(outputs, labels)
                    
                    # backpropagation 
                    loss.backward()
        optimizer.step()
    Grokking Artificial Intelligence Algorithms

    This is an excerpt from Manning's book Grokking Artificial Intelligence Algorithms.

    Using your knowledge of how the Perceptron works, calculate the output for the following:

    A drawing of a person Description automatically generated

    Output node—The output node is a single value representing the predicted class of a specific example or the chance that the example will be in a specific class. The output might be 1 or 0, indicating whether a collision occurred; or it could be something like 0.65, indicating a 65% chance that the example resulted in a collision.

    Zero to AI: A non-technical, hype-free guide to prospering in the AI era

    This is an excerpt from Manning's book Zero to AI: A non-technical, hype-free guide to prospering in the AI era.

    When computers solve tasks we didn’t expect them to be able to perform, we call them AI. After a while, we get used to the latest capabilities, and we stop including them under the umbrella of “AI”. This is called the “AI effect”. The “AI effect” is a well-studied phenomenon that happens every time researchers reach a new milestone in AI research, such as beating the world champion in chess, or building a voice-activated personal assistant. Whenever a new AI technique or algorithm starts working well enough to impact our daily lives, the public opinion starts taking it for granted, stops calling it “AI”, and labels it as just another commodity technology.

    “We’ll use internet data to predict what people will buy”

    sitemap

    Unable to load book!

    The book could not be loaded.

    (try again in a couple of minutes)

    manning.com homepage
    test yourself with a liveTest