Need Help regarding Machine Learning Course

Course Q&A Machine Learning Specialization Unsupervised Learning, Recommenders, Reinforcement
1

Hi

I audited this entire course and understood the theory part.But I need to learn how to code these theory part, can anyone suggest any Youtube videos or something like that.

Thanks in advance!!

2

Not that i know of.

3

Hi @Shyam99 Ask a LLMs to provide code with step by step explanation on the things you’re learning and run in google colab or kaggle notebook.

Let me give you an example:

Use Gemini which is a free LLMs and explain what you are learning and that you need code:

Prompt:

“I am learning gradient descent, can you provide the code with step by step explanation on how to implement gradient descent from scratch”

import numpy as np
import matplotlib.pyplot as plt

# Generate sample data
np.random.seed(0)
X = 2 * np.random.rand(100, 1)
y = 4 + 3 * X + np.random.randn(100, 1)

def compute_cost(X, y, theta):
  m = len(y)
  predictions = X.dot(theta)
  cost = (1 / (2 * m)) * np.sum(np.square(predictions - y))
  return cost

def gradient_descent(X, y, theta, learning_rate, n_iterations):
  m = len(y)
  cost_history = np.zeros(n_iterations)

  for i in range(n_iterations):
    predictions = X.dot(theta)
    error = predictions - y
    theta = theta - (learning_rate / m) * X.T.dot(error)
    cost_history[i] = compute_cost(X, y, theta)

  return theta, cost_history

X_b = np.c_[np.ones((len(X), 1)), X]

theta = np.random.randn(2, 1)
learning_rate = 0.1
n_iterations = 1000

theta, cost_history = gradient_descent(X_b, y, theta, learning_rate, n_iterations)

print("Theta (m, c):", theta)
print("Final Cost:", cost_history[-1])

plt.scatter(X, y)
plt.plot(X, X_b.dot(theta), color='red')
plt.xlabel("X")
plt.ylabel("y")
plt.title("Linear Regression with Gradient Descent")
plt.show()

plt.plot(cost_history)
plt.xlabel("Iterations")
plt.ylabel("Cost (MSE)")
plt.title("Cost History")
plt.show()

Didn’t check the accuracy of the code but looks good.

I hope this helps!

1 Like
4

Worth a shot!!

Thanks a LOT

1 Like