FUNDAMENTALS OF DEEP LEARNING (Francesca Maschio & Matia Polimeno)

work of:Francesca Maschio & Mattia Polimeno

FUNDAMENTALS OF DEEP LEARNING

these are networks of simple nodes, or neurons, that are interconnected and can learn to recognize patterns of input

Each node is connected to several other nodes and has a weight that determines the strength of the connection.

ANNs are similar to the brain in that they are composed of many interconnected processing nodes, or neurons.

is based on artificial neural networks (ANNs)

DEEP LEARNING

LAYER-WISE

Each successive layer extracts more complex features from the previous one until the final output is produced

and so on until the FINAL LAYER(the output layer) produces the desired result

SECOND LAYERcombines these features into more complex patterns

FIRST LAYER OF NEURALNETWORKextracts low-level features from the data (such as edges and shapes)

It can also be used to train a neural network by back-propagating errors from known outputs.

this process is also known as...

can be used to calculate the outputs of deep neural networks for given inputs

FORWARD PROPAGATION

This process of forward and backward propagation is repeated until the error is minimized and the network has learned the desired pattern.

BACKPROPAGATION

is an important part of deep learning because it allows for complex models to be trained quickly and accurately

works by comparing the network's output with the correct output and then adjusting the weights in the network accordingly

is a supervised learning algorithm, which means it requires a dataset with known correct outputs

RECURRENT NEURAL NETWORKS (RNN)

LONG SHORT-TERM MEMORY (LSTM)

CONVOLUTIONAL NEURAL NETWORKS (CNN)

...let's look at some types of deep learning models and neural networks:

CONVOLUTIONAL NEURAL NETWORKS (CNN)

Lare commonly used to analyze visual content. They are similar to regular neural networks, but they have an extra layer of processing that helps them to better identify patterns in images. This makes them particularly well suited to tasks such as image recognition and classification.

RECURRENT NEURAL NETWORKS (RNN)

is a type of artificial neural network where connections between nodes form a directed graph along a sequence. This allows it to exhibit temporal dynamic behavior.

LONG SHORT-TERM MEMORY (LSTM)

are a type of recurrent neural network that can learn and remember long-term dependencies. They are often used in applications such as natural language processing and time series prediction.

THANK YOU!