Deep learning is a subset of machine learning, which in turn is a subset of artificial intelligence (AI). It involves algorithms inspired by the structure and function of the brain called artificial neural networks.
Artificial Neural Networks (ANNs): Deep learning models are based on ANNs, which mimic the way human brains operate. An ANN consists of layers of interconnected nodes or neurons. Each connection can transmit a signal from one neuron to another. The receiving neuron processes the signal and then signals neurons connected to it.
Layers: In deep learning, there are usually three types of layers: the input layer, hidden layers, and the output layer. The "deep" in deep learning refers to the number of layers through which the data is transformed. More layers allow the model to learn more complex patterns.
Learning Process: The learning process in deep learning models involves adjusting the weights of the connections in the neural network based on the data they process and the error in their output. This is often done using a method called backpropagation.
Data-Driven: Deep learning models require large amounts of data to learn from. They excel at identifying patterns in unstructured data such as images, sound, text, and time series.
Applications: Deep learning is used in a variety of applications like image and speech recognition, natural language processing, self-driving cars, and much more.
Digit Classification:
https://github.com/AnalyticalHarry/DeepLearningForDigitClassification
Text to Speech:
https://github.com/AnalyticalHarry/TextToSpeakAlgorithms
Natural Language Processing
https://github.com/AnalyticalHarry/NLPwithTensorFlow
Visualise your neural nets
https://alexlenail.me/NN-SVG/