Review: Log-Sum-Exp Function

Module 4: IDEs & Tools

Log-Sum-Exp Function

Create a NumPy function named log_sum_exp which computes the natural logarithm (base e) of the sum of the exponentials of the input elements. This is a common operation in many statistical computations.

Example:

Input array: [1, 2, 3]
Output: 3.40760596444438

Solution

Try the exercise on your own first, then compare with the worked solution below.

# Solution

def log_sum_exp(arr):
  """
  Computes the logarithm of the sum of exponentiations of the input elements:
  Natural logarithm of the sum of exponentials (base e)
  """
  exp_sum = np.sum(np.exp(arr))
  log_sum_exp_base_e = np.log(exp_sum)

  return log_sum_exp_base_e

# Example array
array = np.array([1, 2, 3])

# Compute the log-sum-exp for the example array
log_sum_exp_result = log_sum_exp(array)
print(log_sum_exp_result)

---
title: "Review: Log-Sum-Exp Function"
subtitle: "Module 4: IDEs & Tools"
format: html
---

## Log-Sum-Exp Function

Create a NumPy function named `log_sum_exp` which computes the natural logarithm (base e) of the sum of the exponentials of the input elements. This is a common operation in many statistical computations.

Example:

- Input array: [1, 2, 3]
- Output: 3.40760596444438

::: {.callout-tip collapse="true"}
## Solution
Try the exercise on your own first, then compare with the worked solution below.

```{python}
# Solution

def log_sum_exp(arr):
  """
  Computes the logarithm of the sum of exponentiations of the input elements:
  Natural logarithm of the sum of exponentials (base e)
  """
  exp_sum = np.sum(np.exp(arr))
  log_sum_exp_base_e = np.log(exp_sum)

  return log_sum_exp_base_e

# Example array
array = np.array([1, 2, 3])

# Compute the log-sum-exp for the example array
log_sum_exp_result = log_sum_exp(array)
print(log_sum_exp_result)
```

:::