Machine Learning Fundamentals : AI Vocabulary (1/4)
We will see in this series somes of the must-know AI vocabulary, the key word of this short serie is “demistifying AI”. By the end of the 4 parts, you will be able to understand all the main concepts related to AI.
Before we begin here is a quick definition of AI according to Chat GPT itself :
Artificial Intelligence (AI) refers to the simulation of human intelligence in machines, enabling them to perform tasks that typically require human intelligence, such as learning, reasoning, problem-solving, understanding natural language, and perceiving their environment. AI encompasses a wide range of techniques and technologies, including machine learning, neural networks, natural language processing, and computer vision, to create systems that can analyze data, make decisions, and adapt to new information or circumstances without explicit programming. AI is used in various applications, from virtual assistants and recommendation systems to autonomous vehicles and medical diagnosis.
Machine Learning Fundamentals :
Machine Learning (ML) :
The ML is a field of study in AI and computer science that aim to use algorithm (cf later on this post) and data to replicate task without any particular instruction, like a human would do but with ever greater accuracy and efficiency througth experiments.
Deep Learning (DL):
DL is a special form of machine learning that involve neural networks with a combination of layer. The more layer a model has, the more accurate the precision will be. Here the human give no instruction about the feature of a specific subject. The layer are composed with many parameters that allow the machine to class and iterate over the input and be able to give the most adequat solution.
Neural Networks :
Neural Networks are computationals models inspired by human brain. They consists of interconnected nodes organized in layer, allowing the system to learn and make decisions based on input data.
Data Science :
Data Science involves extracting knowledge and insights from structured and unstructured data. In the context of Machine Learning, data science plays a crucial role in collecting, cleaning, and analyzing data to train and evaluate models.
Algorithm:
An Algorithm is a step-by-step set of instructions or rules followed by a computer to perform a specific task. In the context of Machine Learning, algorithms are used to make predictions or decisions based on input data.
Training Data:
Training Data is the dataset used to train a machine learning model. It consists of input-output pairs, where the model learns patterns and relationships to make predictions on new, unseen data.
Supervised Learning:
In Supervised Learning, the model is trained on a labeled dataset, where the input data is paired with corresponding output labels. The goal is for the model to learn the mapping between inputs and outputs.
Unsupervised Learning:
Unsupervised Learning involves training a model on unlabeled data, where the algorithm tries to find patterns and relationships without explicit output labels.
Reinforcement Learning:
Reinforcement Learning involves training a model to make sequences of decisions in an environment to maximize a cumulative reward. The model learns by receiving feedback on its actions.
Now that we have setup the main definition of machine learning we will dive deeper in the machine by explorating models training and evaluation.
Thank you all for watching don’t hesitate to make me a feedback, I will be grateful !