We can now notice that with enormous computing power, machines can now recognize objects and translate speech in real time, which allows us to say that intelligence artificial intelligence improves and becomes more intelligent. Adaptations of machines and software to learn in a very real way to recognize patterns in the digital representation of sounds, images or any type of data. While machine learning involves many techniques, deep learning turns out to be a very important approach. There are many definitions of Deep Learning, my favorite being Analytics Vidhya's formal definition of Deep Learning is defined as follows: “Deep Learning is a special type of machine learning that achieves great power and flexibility by learning to represent the world as a nested hierarchy of concepts, with each concept defined in relation to simpler concepts, and more abstract representations calculated in terms of less abstract concepts. »Say no to plagiarism. Get a tailor-made essay on “Why violent video games should not be banned”?Get the original essayDeep Learning is part of a machine learning family. Let's see how Deep Learning came into existence and how it became more popular. As we know, machine learning uses algorithms to analyze data, memorizes it and learns from it, and then decides or predicts what we feed the data into. It is very complex to manually code software with a specific set of instructions to accomplish. a task in machine learning, so the machine is trained using large amounts of data and algorithms that give it the ability to learn itself how to perform the task. The human brain contains billions of neurons that communicate with each other to share information. With the same idea, artificial neurons are created so that the machine makes us think and act like our brain. Using neurons, neural networks were created, the logic was to reproduce the human brain in a machine. The representation of the biological neuron is given in the figure below: Machine learning directly from the minds that dreamed and gave birth to artificial intelligence. The logic was to reproduce the functionalities of the human brain in the machine, hence the concept of neurons. The artificial neurons are represented as shown below: Algorithmic approaches over the years, including decision tree learning, and inductive logic programming are very initial. And there are algorithms like clustering, reinforcement learning, and Bayesian networks. These algorithms failed to achieve the goal of general AI. Delving deeper, we know that one of the most suitable application areas for machine learning for many years was computer vision, and even though that still required a lot of hand coding to accomplish the task. Somehow it even lacked accuracy as an example of reading and recognizing the object during a sunny day and a foggy day. These layers learn through models called “neural networks,” which are structured in layers one after the other. Deep learning is called an artificial neural network (ANN), which is a trained network inspired by biological neural networks that can be used to approximate functions that have a huge number of rarely known inputs. Simple neural networks lacked the precision to make the system more robust and powerful... 6848-6856).