Deep Learning::Numpy in Machine Learning

NumPy is a Python library used for numerical computing that provides support for arrays and matrices, along with a collection of mathematical functions to operate on these data structures.

A NumPy array is a grid of values, all of the same type, and is indexed by a tuple of nonnegative integers.

You can create a 2D NumPy array using `numpy.array([[1, 2], [3, 4]])`.

The `reshape` method changes the shape of an array without changing its data.

You access elements in a NumPy array using indexing, e.g., `array[0]` for the first element.

`numpy.zeros` creates an array filled with zeros, given the shape specified.

`numpy.ones` creates an array filled with ones, given the shape specified.
```
shape = (3, 4) # 3 rows and 4 columns
ones_array = np.ones(shape)
```

Broadcasting refers to how NumPy handles arithmetic operations on arrays of different shapes.

```
import numpy as np

# Create a 2D array and a 1D array
array_2d = np.array([[1, 2, 3],
[4, 5, 6]]) # Shape: (2, 3)
array_1d = np.array([10, 20, 30]) # Shape: (3,)

# Broadcasting the 1D array across each row of the 2D array
result = array_2d + array_1d

print("2D array shape:", array_2d.shape)
print("1D array shape:", array_1d.shape)
print("Result shape:", result.shape)
print("\n2D array:")
print(array_2d)
print("\n1D array:")
print(array_1d)
print("\nResult after broadcasting:")
print(result)
```
## Output
```
2D array shape: (2, 3)
1D array shape: (3,)
Result shape: (2, 3)

2D array:
[[1 2 3]
[4 5 6]]

1D array:
[10 20 30]

Result after broadcasting:
[[11 22 33]
[14 25 36]]
```