Machine Learning

You might also like

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 2

Machine Learning (freecodecamp)

Artificial Intelligence (A.I) – effort to automate intellectual tasks normally performed by humans.

- No layers

History:

1950 – can computers think? A.I coined

A.I- predefined set of rules

Machine learning- figures out the rules for us.

Goal for machine learning models: highest accuracy possible

Summary: rather than giving the program the rules, an algorithm finds the rules for us.

- Has 1 or two layers

Neural Networks (deep learning) – a form of machine learning that uses a layered representation of data.

Data is transformed to different layers

Tensor – a generalization of vectors and matrices to potentially higher dimension. Internally, TensorFlow represent tensors as n-
dimensional arrays of base datatypes.
Vector – can have any amount of dimensions

Each tensor represents a partially defined computation that will eventually produce a value.

-has a data type and a shape..

Data type -what kind of information is stored in the tensor (e.g.g float32, int32, string and others.

Shape – the represents the dimension of data.

Creating Tensors:

String: tf.Variable(“this is a string”, tf.string)

Number = tf.Variable(324, tf.init16)

Floating- = tf.Variable(3.567, tf.float64)

Rank/Degree of Tensors

- Number of dimensions involved in the tensor.

Rank0 – scalar
Rank1 – array, list – can store more than one value in more than one dimension
Rank2 – deep level of nested list; matrices

Shape of Tensor – how many items we have in each dimension

Tf.rank(rank2_tensor)

Ranl2_tensor.shape
Changing Shape – reshape data

Types of Tensors

- Variable
- Constant
- Placeholder
- SparseTensor

You might also like