Fundamentals of deep learning

Fundamentals of deep learning

Index

Neuron

Human vs Machine

Introdution of A.I.

Sigmoid neuron

Deep neural network

Artificial neurons

Why is it so important?

Applications

Team and thanks

Artificial Intelligence

A. I.

Alan Turing is considered a father of theoretical computer science and artificial intelligence. He created the Turing Test,

Human vs Machine

The brain is the most incredible organ in the human body and it is what makes us intelligent. It dictates the way we perceive every sight, sound, smell, taste, and touch.The foundational unit of the human brain is the neuron.

Traditional computer programs are designed to be very good for performing arithmetic really fast and explicitly following a list of instructions, but it has difficulty solving recognition problems between two similar things, such as a 6 and a 0 written by a human

Axon

Dendrites

Cell body

Presynaptic axon terminal

Axon terminal

Neuron

A tiny piece of the brain, about the size of grain of rice, contains over 10,000 neurons. It’s this massive biological network that enables us to experience the world around us. Our goal will be to use this natural structure to build deep learning models that solve problems in an analogous way. At its core, the neuron is optimized to receive information from other neurons. The neuron receives its inputs along antennae-like structurescalled dendrites. Each of these incoming connections is dynamically strengthened or weakened based on how often it is used (this is how we learn new concepts), and it’s the strength of each connection that determines the contribution of the input to the neuron’s output.

Artificial neurons

We can translate this functional understanding of the neurons in our brain into an artificial model that we can represent on our computer. Our artificial neuron takes in some number of inputs, x1, x2, . . . , xn, each of which is multiplied by a specific weight, w1, w2, . . . ,wn. These weighted inputs are, as before, summed together to produce the logit of the neuron. The logit is then passed through a function f to produce the output y = f z . This output can be transmitted to other neurons.

Deep neural network

To tackle much more complicated tasks, we’ll have to take our machine learning model even further. The neurons in the human brain are organized in layers. Information flows from one layer to another until sensory input is converted into conceptual understanding. This information is processed by each layerand passed on to the next until, we conclude whether we are looking, for example, at a cat, or a soda can, or an airplane. Borrowing from these concepts, we can construct an artificial neural network.

Sigmoid neuron

The building block of the deep neural networks is called the sigmoid neuron, which uses the function on the left. When the logit is very small, the output of a logistic neuron is very close to 0. When the logit is very large, the output of the logistic neuron is close to 1. In-between these two extremes, the neuron assumes an S-shape. there are other models of functions.

Why is it so important?

Even if the demand for huge computational capacities can represent a limit, the scalability of Deep Learning thanks to the increase in available data and algorithms is what differentiates it from Machine Learning: Deep Learning systems, in fact, improve their performance 'increase data while Machine Learning applications when they reach a certain level of performance are no longer scalable even by adding examples and training data to the neural network. The computational calculation required for their operation is really impactful, also from an economic point of view, it requires excellent CPU and GPU.

Applications of deep learning

Face recognition

Virtual assistans

Autonomous Vehicles

Chatbots

Colorization of images

Sound addition

Thanks!

The work was created by Salvatore Farina and Giacomo Italiano