Deep learning
Deep learning (also known as deep structured learning) is part of a broader family of machine learning methods based on artificial neural networks with representation learning. Learning can be supervised, semi-supervised or unsupervised.
Machine learning is turning things(data) into numbers and finding patterns in those numbers.
Structured data Unstructured data
| Shallow algorithms | Common algorithms |
|---|---|
| Random forest | Neural networks |
| Naive bayes | Fully connected neural network |
| Nearest neighnour | Convolutional neural network |
| Support vector machine | Recurrent neural network |
| Transformer | |
| and many more | and many more |
| Structured data | # Unstructured data |
Depending how you represent your problem many algorithms can be used for both.
A neural network is a **network or circuit of neurons**, or in a modern sense, an artificial neural network, composed of artificial neurons or nodes. Thus a neural network is either a biological neural network, made up of biological neurons, or an artificial neural network, for solving artificial intelligence (AI) problems.
Neural Network
Anatomy of Neural Networks
Types of learning
What is TensorFlow
- End-to-end platform for machine learning
- Write fast deep learning code in python/other accessible languages(able to run on a GPU/TPU)
- Able to access pre-built deep learning models(TensorFlow Hub)
- Whole stack: preprocess data, model data, deploy model in your application
- Originally designed and used in-house by Google(now open-sources)
GPU/TPU
Graphic Processing Unit
Tensor Processing Unit
Tensor Processing Unit (TPU) is **an AI accelerator application-specific integrated circuit (ASIC) developed by Google specifically for neural network machine learning, particularly** using **Google's own TensorFlow software.**
What is a tensor?
In mathematics, a tensor is an algebraic object that describes a multilinear relationship between sets of algebraic objects related to a vector space. Objects that tensors may map between include vectors and scalars, and even other tensors. There are many types of tensors, including scalars and vectors (which are the simplest tensors), dual vectors, multilinear maps between vector spaces, and even some operations such as the dot product. Tensors are defined independent of any basis, although they are often referred to by their components in a basis related to a particular coordinate system.
What we're going to cover
- Tensorflow basics and fundamentals
- Preprocessing data(getting it into tensors)
- Building and using pretrained data(learning patterns)
- Making predictions with a modal(using the patterns)
- Evaluating model predictions
- Saving and loading models
- Using a trained model to make predictions on custom data
