Deep Learning Dictionary - Lightweight Crash Course

Machine Learning - Deep Learning Dictionary

Machine learning (ML) is a subfield of AI that uses algorithms to analyze data, learn from that data, improve, and then make a determination or prediction about new data.

The key distinction of machine learning algorithms as opposed to traditional non-ML algorithms is that ML algorithms learn from the data.

With machine learning, rather than a developer manually writing code with an explicit set of instructions to accomplish a specific task (as with traditional programming), the machine is instead trained using data and algorithms that give it the ability to learn from the data and perform the task without explicitly being told how to do so.

With a traditional programming approach, we might write a program that would classify an article from a health magazine as either "diet" or "exercise" based on whether the number of counted "diet words" was greater than or less than the number of "exercise words."

These words would be chosen by the developer. When there is a higher number of diet words, then the article is classified as a diet article. When there is a higher number of exercise words, the article is classified as exercise.

# pseudocode
diet = [
    "diet", 
    "food", 
    "eat"
]

exercise = [
    "exercise", 
    "movement", 
    "weightlifting"
]

On the other hand, with machine learning, we supply an algorithm with a dataset containing articles from the health magazine, and each article has been labeled by us as either being "diet" or "exercise."

# pseudocode
articles = [
    {
        label: "diet",
        data: "Wholegrains are a great source of fiber..."
    },
    {
        label: "diet",
        data: "Processed meats, like hotdogs..."
    },
    {
        label: "exercise",
        data: "Once your heartrate reaches..."
    },
    {
        label: "exercise",
        data: "Squats activate the quads..."
    }
]

Through some training process, the algorithm will analyze the data and learn the features that classify what a diet article looks like versus a exercise article.

With what it has learned from the dataset, the algorithm can then classify new articles as diet or exercise, although it was never given explicit instructions for how to do this classification from the developer of the program.

Within the field of machine learning, there are many types of learning algorithms that work with all types of data to achieve all sorts of tasks. Some common ML algorithms include:

• Regression
• Decision Trees
• Support Vector Machines (SVM)
• Naive Bayes Classifiers
• K-Nearest Neighbor
• Artificial Neural Networks (belongs to subfield of deep learning)