The Artificial Intelligence dictionary for beginners
Under the name Artificial Intelligence lies many different concepts often misunderstood and misused in the public sphere.
Our aim with this dictionary is to explain in a simple yet accurate way the many terms related to Artificial Intelligence.
Feel free to give us your feedback at info@heuritech.com. Let’s get started! 🤓
P.S: words marked with an asterisk (*) are defined in the dictionary
A*
Artificial Intelligence (AI)
A tricky one to start with because there isn’t an homogenous definition. We’ve asked our R&D team which led to a long and passionate debate. Here is what came out:
- Today, we can define AI as intelligent programs that achieve tasks usually tackled by humans.
- In the future, AI could be human intelligence autonomously reproduced by a program.
- One definition everyone agrees on: AI is a field of research which includes Machine Learning*, Deep Learning*, Natural Language Processing*, Visual Recognition*, among others.
Algorithm
An algorithm is a succession of simple instructions that achieves a predetermined goal. Let’s take a concrete example: getting dressed every morning (because who doesn’t find it hard?). You follow a strict process: first, underwears, then clothes, and finally, shoes. That’s exactly what an algorithm does: follow instructions to answer a problem.
Attributes
The characteristics of an “object”: it could be anything ranging from colors, textures, shapes, etc. For example: what is Jeanne Damas below wearing? You can find next to the picture all the attributes composing her outfit.
C*
Classification
Classification consists in organising pieces of data into categories. In Heuritech’s case, these pieces of data correspond to images, and the categories might be different types of garments (i.e. bags, shoes, dresses, pants). To train a classification model, data scientists need labelled data*.
Clustering
A clustering model automatically groups together images that share common characteristics. Interestingly, the model groups images without being trained to group images.
Computer Vision
Computer Vision is one branch of Artificial Intelligence focused on image and video and also called visual recognition*.
D*
Detection
A detection model localises and classifies one or many objects in a picture. To visually represent the output of a detection model, rectangles are drawn (also called bounding boxes) around the detected object.
Data set
A list of curated data gathered to train a model or to evaluate its performance. In our case, the data set is composed of images, mostly related to fashion. For further explanation, see also labelled data*.
Deep Learning (a branch of Machine Learning)
Deep learning is a subfield of machine learning* that has revolutionised artificial intelligence* these past ten years.
Visual recognition* has particularly benefit from advances in Deep Learning, making it possible to recognize, detect and segment objects in images with a very high performance. A deep learning model learns to recognize concepts that make sense for us humans, such as a landscape, handbags, a smiling face etc.
To do so, it finds the most significant elementary contours and shapes, and combines them to create more complicated patterns, which will also be combined to create even more complicated patterns, etc. At the end of this process, often referred to as a multi-layered, the model predicts one of the classes* it has been trained on.
G*
Generalization
The ability of a machine learning* algorithm* to perform well on pictures it has never seen. If the model is trained on a set of 1000 images, will it be able to have good results on every other image?
H*
Heuristic.
The scientific art of making discoveries. From the greek word eurisko (“I believe”) that led to “Eureka”, which was popularized by Archimede when he discovered the Archimedes’ principle in his bath. The Heuristic approach consists of progressively eliminating all alternatives to find a working and applicable solution.
Heuritech.
Composed of two names : heuristic and technology. Also composed of 25 brains that together form Heuritech, a start-up whose mission is to build the best visual recognition tailored to consumer industries. By uniquely applying this state-of-the-art technology to millions of Instagram pictures each day, we are able to monitor products and trends. This is achieved thanks to continuous R&D led since 5 years by the Heuritech team composed of 35% of PhDs in AI.
L*
Labelled data
The goal of a machine learning* model* is to predict the right output given an input. For instance, some models that we use at Heuritech are able to predict specific handbag type (output) given an image (input). These models are trained on labelled data, i.e. a set of images along with their tag*.
Training a model is very costly, partly because it requires a few thousands labelled data that humans usually need to label one by one. In Heuritech’s case, labelled data consist in a set of pictures that are associated to fashion attributes.
M*
Machine Learning (a branch of AI)
As a reminder, an AI* is a program that achieves tasks usually tackled by humans. One of the ways to build this AI is to use Machine Learning models. These models have the ability to learn using labelled data*. For example, if you want the model to recognize dresses in pictures, you will show it a few hundreds of pictures and tell it they correspond to dresses. You will do so until it is able to recognize them in pictures it has never seen before (see Generalization*).
Model
A mathematical model is a way of understanding the world through equations. But the world is actually quite restricted since it’s only made of the type of data our model is able to read (be it images, sounds, texts, stock prices, …).
Given an input, a model is trained to provide a proper output. In the case below, the input is an image and the output is a localised attribute, e.g. the handbag.
In machine learning, all models are trained with data to behave in a specific way.
Heuritech’s model:
Input: Picture from Instagram
Output: detection of the handbag
N*
Neural network
Picture a brain and you have a neural network: i.e. a network composed of millions of units that make layered calculations to achieve a decision. Just like we do when we think.
Natural Language Processing (NLP)
A branch of Artificial Intelligence* focus on text. The name is pretty self explanatory: the machine is processing the natural (=human) language. That’s how for example spam emails end up in the spam mailbox: because your email uses an NLP system trained to recognise and filter spams.
P*
Pattern
A structure in the data* that repeats itself. The model* automatically learns to extract, recognize and characterize patterns.
Precision & Recall
Precision and recall are metrics used to measure the performance of a model*.
Precision: For everything that your model predicts, what is the proportion of correct ones?
Recall: For everything that your model should find, what proportion is effectively found?
Let’s take a concrete example.
Below is a basket with 6 apples and 3 peaches. We ask a model to find the apples. This model, not so performant, considers that they are 5 apples where in reality it’s 3 apples and 2 peaches.
- The precision of this model is 3/5 = 60%, i.e. 3 correct apples among 5 apple predictions.
- The recall of this model is 3/6 = 50%, i.e. among the 6 apples that are in the basket, 3 of them are found.
S*
Segmentation
Image segmentation automatically draws the contours of an object. Segmentation is useful for many functionalities such as color extraction or garment recognition.
In the gif below, you can see both bounding boxes (rectangles surrounding the object) and segmentation (the contour of the object itself), which are automatically generated by a machine learning* model*.
T*
Tagging
Tagging is to artificial intelligence* as hashtag is to Instagram. Each image could be associated to tags, for example, #tshirt, #red, #cropped, etc.
See also: classification
V*
Visual recognition (also called Computer Vision)
One of Artificial Intelligence’s* branch focused on images, hence the name visual + recognition. A model can be trained to recognize specific items in pictures: such as clothes in Heuritech’s case.
We hope you liked the Artificial Intelligence Dictionary!
Feel free to give us your feedback and propose new definitions at info@heuritech.com
This dictionary will be updated regularly. If you want to stay in touch with latest news, subscribe to our monthly newsletter about artificial intelligence and fashion.
Heuritech empowers fashion teams to monitor in real time both products and trends through cutting-edge image recognition technology applied on millions of social media images every day.
