AI & Machine Learning

Development machine is a platform for development. For example, setting your PC for troubleshooting program bugs.

Artificial Intelligence (AI) – program that can sense, reason, act, and adapt

Today, artificial intelligence(AI) is a thriving field with many practical applications and active research topics. We look to intelligent software to automate routine labor, understand speech or images, make diagnoses in medicine and support basic scientific research.

Machine Learning (ML)

AI systems which has the ability known as machine learning to acquire their own knowledge.

ML is the process of training what’s known as model to evaluate external data set that is fed to it and act upon.

Machine Learning frameworks/libraries such as Caffe and TensorFlow are ML model development tools.

Neural Network

(i.e. mimics cognitive functions in having the ability to learn and reason like humans)

Convolutional neural networks are distinguished from other neural networks by their superior performance with image, speech, or audio signal inputs. They have three main types of layers, which are:

  • Convolutional layer
  • Pooling layer
  • Fully-connected (FC) layer

Convolutional layer

Layers are in 3D: Height, Width, Depth (corresponds to RGB for color image as pixel input)

Neurons of one layer connects to an area of the next which continues till the final (output) layer.

Feature detector (a.k.a. filter/kernel), a 2D matrix of weights, which sweeps across the input layer.

Convolutional layer (output) is the dot product of the input layer and feature detector.

Pooling Layer

Similar to the convolutional layer but without weights (uses aggregation function (single value from a set of values, e.g. 5 from (10+5+0)/3) on the input layer instead), it downsamples to reduce dimensionality for lesser complexity which produces higher efficiency.

Fully-Connected (FC) Layer

Flattens input to 1D and optimizes it such as performing classification.

Deep Learning

Subset of machine learning.

By gathering knowledge from experience, this approach avoids the need for human operators to formally specify all the knowledge that the computer needs. The hierarchy of concepts enables the computer to learn complicated concepts by building them out of simpler ones. If we draw a graph showing how these concepts are built on top of each other, the graph is deep, with many layers (multilayered neural networks). For this reason, we call this approach to AI deep learning.

Supervised & Unsupervised Learning

Supervised Learning

Supervised learning is a type of ML where the model is provided with labeled training data.


Leaf width and leaf length are the features (which is why the graph below labels both of these dimensions as X), while the species is the label.

In supervised machine learning, you feed the features and their corresponding labels into an algorithm in a process called training.

During training, the algorithm gradually determines the relationship between features and their corresponding labels. This relationship is called the model (pattern).

Now that a model exists, you can use that model to classify new plants (unknown) that you find.

Unsupervised Learning

In unsupervised learning, the machine must learn from an unlabeled data set.

In other words, the model has no hints how to categorize each piece of data and must infer its own rules for doing so.

Sometimes the model finds patterns in the data that you don’t want it to learn, such as stereotypes or bias.

Common supervised and unsupervised ML problems

Type of ML ProblemDescriptionExample
ClassificationPick one of N labelsCat, dog, horse, or bear
RegressionPredict numerical valuesClick-through rate
ClusteringGroup similar examplesMost relevant documents (unsupervised)
Association rule learningInfer likely association patterns in dataIf you buy hamburger buns, you’re likely to buy hamburgers (unsupervised)
Structured outputCreate complex outputNatural language parse trees, image recognition bounding boxes
RankingIdentify position on a scale or statusSearch result ranking

Regression is a return to earlier stages of development and abandoned forms of gratification belonging to them, prompted by dangers or conflicts arising at one of the later stages. 

Can technically estimate linear regression by using the y = mx + c straight line formula. For example, we can predict y = 11 when m = 2; x = 4; c = 3. If actual data is 12, our offset will be 1.


  1. 6, May, and Walker Rowe. “What Is a Neural Network? An Introduction with Examples.” BMC Blogs, 6 May 2020,
  2. By: IBM Cloud Education. “What Are Convolutional Neural Networks?” IBM,
  3. Deep learning. Deep Learning. (n.d.). Retrieved February 25, 2022, from