Skip to main content
pelatihan
.org
Learn. Practice. Grow.
Category
EN
Sign in
Sign up
Menu
A.I. Curriculum: 8 Chapters, 55 Lessons — pelatihan.org
Home
/
Catalog
/
A.I.
/
Curriculum
Curriculum
A.I. Curriculum
Learn A.I. online with 55 structured lessons, code examples, and 275 quiz questions.
55 lessons
8 chapters
275 questions
Summaries and key points are free to preview. Full lessons, code examples, and quizzes require a subscription.
01
Machine Learning
18 lessons
01
ML Intro
Artificial Intelligence (AI): the field of computer science that enables machines to perform tasks that normally require human intelligence. AI is everywhere, from virtual…
02
ML and AI
This lesson explains the relationship between AI and machine learning: AI is the ultimate goal of making machines intelligent, whereas machine learning is an approach to how…
03
ML Languages
There are many programming languages that are used to build AI systems and machine learning. Python is most popular for its simple syntax and complete libraries, such as NumPy,…
04
ML JavaScript
JavaScript allows us to create AI applications directly in a browser without a dedicated computing server. Popular libraries in this ecosystem are Brain.js for neural networks…
05
ML Examples
This page shows a number of real-world examples of AI and machine learning applications. The patterns that machines learn can be numbers, text, images, or sounds, and then they…
06
ML Linear Graphs
A linear graph is a straight line representing a function of the form y = mx + b. In machine learning, linear lines are used to model simple relationships between features and…
07
ML Scatter Plots
A scatter plot displays data as dots on a field of coordinates to see the relationship between two variables. The dot pattern helps us guess whether there's a positive…
08
ML Perceptrons
The Perceptron is the simplest model of machine learning, equivalent to one artificial neuron. It receives some input, multiplies it by weight, sums it up with bias, and then…
09
ML Recognition
Pattern recognition is the task of AI to recognize the shape, image, or sound of raw data. The image is converted into a pixel-number matrix so that it can be processed by a…
10
ML Training
Training is the process of training a model with data so that it can guess the correct output and correct the weight of the error. This process is repeated many times (epoch)…
11
ML Testing
After training, the model must be tested with unprecedented data to measure the actual capability. The test results are usually expressed as a percentage of accuracy, which is…
12
ML Learning
Machine learning has three main approaches: supervised, unsupervised, and reinforcement learning. Supervised uses labeled data, unsupervised groups unlabeled data, and…
13
ML Terminology
Understanding the basic terms of machine learning makes it easy for us to read documents and model code. Key terms include features (input characteristics), labels (predicted…
14
ML Data
Data is the main ingredient of machine learning: without quality data, models are useless. Data is generally divided into training data for learning and data testing to gauge the…
15
ML Clustering
Clustering is an unsupervised learning technique for grouping similar data without labeling. Popular algorithms include K-Means which divide data into K groups based on…
16
ML Regressions
Regression is used to predict continuous values such as price, temperature, or weight. Linear regression looks for the best straight line that approaches the entire data point by…
17
ML Deep Learning
Deep learning uses a neural network made up of multiple layers of neurons. Each neuron adds the input weighed, adds bias, and then passes the result to an activation function…
18
ML Brain.js
Brain.js is a JavaScript library that makes it easy to create and train neural networks without complicated configuration. Just set up the array of input and output pairs, and…
02
TensorFlow
4 lessons
01
TFJS Tutorial
TensorFlow.js is a library for running the TensorFlow machine learning model in JavaScript, both in browsers and Node.js. The data in TensorFlow is represented as tensors, a…
02
TFJS Operations
TensorFlow provides basic operations on tensors such as addition, subtraction, division, and multiplication of elements per element. In addition there is a matrix operation such…
03
TFJS Models
In TensorFlow.js, the model is usually made with tf.sequential() in the form of a layer stack, e.g. tf.layers.dense. Once the network structure is compiled, the model is compiled…
04
TFJS Visor
Tfjs-vis is the official library for visualizing data and training processes in browsers. The tf.visor() function opens a visualization panel containing a surface that can…
03
Example 1
4 lessons
01
Ex1 Intro
The first example TensorFlow.js predicts the value of y from the value of x having a near-linear relationship. We set up the data in tensors x and y, we make a simple model, then…
02
Ex1 Data
The data in TensorFlow.js is made tensor with tf.tensor1d for vectors and tf.tensor2d for matrices. The neat data makes models easy to train and the results easy to read. In a…
03
Ex1 Model
The model is made with tf.sequential() and then a dense layer is added as needed. For simple regression, just one layer with one neuron, configured with the loss meanSquaredError…
04
Ex1 Training
Training is conducted with model.fit(xs, ys, {epochs: n}) which repeats the learning process n times over the entire data. Each epoch, the weight is adjusted to reduce the loss.…
04
Example 2
4 lessons
01
Ex2 Intro
The second example predicts the price of a home from several features at once, such as the area, the number of rooms, and the age of the building. Since the output is a…
02
Ex2 Data
Before practicing a home price model, the data was normalized by dividing each value by its maximum value so that it was in the range of 0 to 1. The data is also divided into…
03
Ex2 Model
Models for home prices use inputShape according to the number of features, for example 3, with a hidden layer activating ReLU and one output neuron for the price. Loss remains…
04
Ex2 Training
Once the house price model is ready, the training is run with normalized data, often with a particular batchSize so that weight updates occur more frequently. After training, the…
05
JS Graphics
6 lessons
01
Graph Intro
Data visualization helps us understand the patterns behind a set of numbers. JavaScript offers many options for creating graphics, ranging from manual canvas to ready-to-use…
02
Graph Canvas
HTML5 canvas provides a fully controlled drawing area via JavaScript. With 2D context objects, we can create lines, circles, text, and other shapes to visualize the data…
03
Graph Plotly.js
Plotly.js is a JavaScript library for creating interactive graphics such as scatter plots, lines, bars, and more. Just set up arrays x and y, specify the mode and type of the…
04
Graph Chart.js
Chart.js is a lightweight JavaScript library for creating graphs such as bars, lines, and circles over canvas elements. We just create the Chart object with the desired type,…
05
Graph Google
Google Charts is a Google visualization service that is uploaded directly from the internet via google.charts.load(). The data is prepared in the form of a table, then a specific…
06
Graph D3.js
Data-Driven Documents is a library for manipulating DOM and SVG based on data. We tie the data to the element, and then D3 creates or modifies the element automatically according…
06
History
8 lessons
01
History of Intelligence
Human intelligence is born of a brain that contains billions of interconnected neurons. Each neuron receives a signal, processes it, and then transmits the output signal to…
02
History of Languages
Programming languages evolved from computer-compromised binary machine code, then assembly languages with abbreviations, to high-level languages like Fortran, Lisp, Python, and…
03
History of Numbers
Before the modern computer, humans had developed a number system and tools like the abacus. Modern computers process everything in a binary number system (base 2) because…
04
History of Computing
The history of computers records four great generations based on its main technology: vacuum tubes, transistors, integrated circuits, to microprocessors. Each generation produced…
05
History of Robots
A robot is a machine that can perform automated tasks, often with sensors and program controllers. The word 'robot' was popularized in Karel Čapek's play R.U.R. It then developed…
06
History of AI
The history of AI began with Alan Turing's idea of thinking machines, including the Turing test in 1950. The Dartmouth Conference in 1956 officially gave birth to the field of…
07
Job Replacements
Many people worry that AI will replace human work, but the reality is more diverse. AI automates repetitive tasks based on clear rules, while creating new roles and changing the…
08
Theory of Mind
The concept of mind theory is a stage of AI that is capable of understanding the mental state, emotions, and intentions of others, similar to human social ability. AI today is…
07
Mathematics
6 lessons
01
Mathematics
Machine learning focuses on several branches of mathematics, especially linear algebra, calculus, and statistics. Linear algebra is used to represent data and weights as vectors…
02
Linear Functions
The linear function y = mx + b is the basis of many machine learning concepts. The value m is the gradient that determines the line curvature, whereas b is the cut-off point on…
03
Linear Algebra
Linear algebra studies vectors and matrices that are the main language of machine learning. Training data, layer weight, to predictive results are all represented as matrix.…
04
Vectors
A vector is a sequential list of numbers that represents a point or feature in multidimensional space. The two basic vector operations are the addition of elements per element…
05
Matrices
Matrix is a row and column table that is the most commonly used data structure in machine learning. The identity matrix is like the number 1 in multiplication, so multiplying the…
06
Tensors
Tensor is the generalization of scalars, vectors, and matrices to a larger number of dimensions. Scalars are 0, vectors are 1, matrix is 2, and so on. Deep learning works fully…
08
Statistics
5 lessons
01
Statistics
Statistics is the science of collecting, analyzing, and interpreting data, and it's the backbone of machine learning. The core concepts include mean, median, distribution,…
02
Descriptive
Descriptive statistics summarize the data into a few concise numbers: mean (average), median (middle value), and mode (value most frequently occurring). All three give a quick…
03
Variability
Variance and standard deviation measure how far the data values spread from their mean. The variance is the square root of the difference of each value to the mean, whereas the…
04
Distribution
Distribution describes how the values in a data are distributed. The most famous form is the symmetrical normal distribution (bell curve) around the mean, with extreme values…
05
Probability
Probability measures the probability of an event occurring, ranging from 0 (impossible) to 1 (certain). This concept became the basis of predictive models such as classification…