AP®︎/College Computer Science Principles
Machine learning algorithms
Machine learning (ML) is a type of algorithm that automatically improves itself based on experience, not by a programmer writing a better algorithm. The algorithm gains experience by processing more and more data and then modifying itself based on the properties of the data.
Types of machine learning
There are many varieties of machine learning techniques, but here are three general approaches:
- reinforcement learning: The algorithm performs actions that will be rewarded the most. Often used by game-playing AI or navigational robots.
- unsupervised machine learning: The algorithm finds patterns in unlabeled data by clustering and identifying similarities. Popular uses include recommendation systems and targeted advertising.
- supervised machine learning: The algorithm analyzes labeled data and learns how to map input data to an output label. Often used for classification and prediction.
Let's dive into one of the most common approaches to understand more about how a machine learning algorithm works.
An increasingly popular approach to supervised machine learning is the neural network. A neural network operates similarly to how we think brains work, with input flowing through many layers of "neurons" and eventually leading to an output.
Diagram of a neural network, with circles representing each neuron and lines representing connections between neurons. The network starts on the left with a column of 3 neurons labeled "Input". Those neurons are connected to another column of 4 neurons, which itself connects to another column of 4, and those neurons are labeled "Hidden layers". The second hidden layer of neurons is connected to a column of 3 neurons labeled "Output".
Training a network
Computer programmers don't actually program each neuron. Instead, they train a neural network using a massive amount of labeled data.
The training data depends on the goal of the network. If its purpose is to classify images, a training data set could contain thousands of images labeled as "bird", "airplane", etc.
A grid of images in 10 categories (airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck).
The goal of the training phase is to determine weights for the connections between neurons that will correctly classify the training data.
A diagram of a neural network classifying an image of a plane. Parts of the image are fed into the first layer of neurons, those neurons lead to a middle layer, and those neurons lead to a final layer of neurons. Each edge between neurons is labeled with a question mark, denoting an unknown weight.
The neural network starts off with all the weights set to random values, so its initial classifications are way off. It learns from its mistakes, however, and eventually comes up with a set of weights that do the best job at classifying all of the training data.
A diagram of a neural network classifying an image of a plane. Parts of the image are fed into the first layer of neurons, those neurons lead to a middle layer, and those neurons lead to a final layer of neurons. Each neuron has a weight (from 0 to 1). In the final layer, the neuron labeled "plane" has the highest weight.
Using the network
When the neural network is asked to classify an image, it uses the learned weights and outputs the possible classes and their probabilities.
Diagram of a neural network, with circles representing each neuron and lines representing connections between neurons. The network starts on the left with an image of a fox. The image is broken into 4 parts, and those parts are connected to column of 4 neurons, which itself connects to another column of 4. The second column is connected to 3 possible outputs: "Fox (0.85)", "Dog (0.65)", and "Cat (0.25)".
The accuracy of a neural network is highly dependent on its training data, both the amount and diversity. Has the network seen the object from multiple angles and lighting conditions? Has it seen the object against many different backgrounds? Has it really seen all varieties of that object? If we want a neural network to truly understand the world, we need to expose it to the huge diversity of our world.
Companies, governments, and institutions are increasingly using machine learning to make decisions for them. They often call it "artificial intelligence," but a machine learning algorithm is only as intelligent as its training data. If the training data is biased, then the algorithm is biased. And unfortunately, training data is biased more often than it's not.
In the following articles, we'll explore the ramifications of letting machines make decisions for us based on biased data.
🙋🏽🙋🏻♀️🙋🏿♂️Do you have any questions about this topic? We'd love to answer—just ask in the questions area below!
Want to join the conversation?
- Please reveal the equations required to adjust the weights. Thx.(3 votes)
- The algorithm is called backpropagation/gradient descent. Basically, find negative gradient for cost function (Predict-Real result)^2 and then change the weights by the gradient(2 votes)
- how does the ai know how which node to pass the information to(1 vote)
- That's what the learning part of machine learning is for. Many neural networks are trained through thousands of slightly different iterations, oftentimes using Darwinian algorithms for each group so that it takes the best method from that group and then slightly modifies it into a new group of iterations, continuing this process to get the "perfect model", which is, of course, not perfect but given tens or hundreds of thousands, maybe even millions of total iterations over hundreds of "generations", it tends to come out well, as long as the training data is solid.(2 votes)
- in the labeled data sets, how is a dog distinguished from a wolf? Are the pictures reduced to mathematical point, for example, distance between eyes, length of ears?(1 vote)
- In labeled datasets, humans look at the pictures and tag them accordingly.(0 votes)
- Hi! Does Khan Academy use machine learning and AI anywhere on the platform? Does the Course Mastery system, and decisions of which questions to display in an attempt of the Course Challenge, Unit Test, or Mastery Challenge, use ML or AI? Does the LSAT and SAT practice use machine learning? I'm looking for concrete examples of ML and AI that I engage with everyday. And Khan Academy is the best place to start!(0 votes)
- The course mastery system is a basic algorithm: It presents questions (tagged with what practice they're from), and at the end it goes through all the practices and ups your level by on the ones you did good at, and if you did bad it lowers your level on the ones you did bad at. If you got all questions right, it ups your level twice on all the questions asked.
Well, that's how it works for the quizzes, unit tests, and course tests. The individual quizzes are much simpler. If you get some amount of questions right (I think it's 75% or above), your level is set to one bar. If you get all the questions right, your level is set to two bars.
At least, that's from my experience. I don't actually know KhanAcademy's internal code, but that's the algorithm that makes the most sense with what I've seen.(0 votes)
- How do I make machine learning in python?(0 votes)
- There are numerous tutorials on the internet that go through how to use python machine-learning libraries, such as PyTorch and TensorFlow.(0 votes)
- If this is a neural network, what is a deep neural network then?(0 votes)
- A deep neural network is a neural network that has multiple hidden layers.(0 votes)