Dataford
Interview QuestionsInterview GuidesExperiencesMock InterviewsPricing
Get started

Neural Network From Scratch

HardPython00:00
Practice interviewer
In session
5 left
00:00

Your question is Neural Network From Scratch. Start with the requirements on the right.

Run and submit as often as you like. When you're ready, talk me through your approach or go straight to the code.

You need to log in / sign up to run or submit.

Problem

Bell’s network analytics team needs a lightweight binary classifier that can run without a machine learning framework. Implement a fully connected neural network from scratch using only Python lists and arithmetic.

Your function must train a network with one hidden layer and return a binary prediction for every input row. Use tanh in the hidden layer, sigmoid in the output layer, binary cross-entropy gradients, and full-batch gradient descent. Initialize weights deterministically so repeated calls produce the same predictions.

Formal Specification

Implement neural_network(X, y, hidden_size, learning_rate, epochs), where X is a non-empty list of rows containing numeric features and y is a list of binary labels. The function returns a list of integers, each either 0 or 1, in the same order as the input rows.

Initialize input-to-hidden weights using 0.05 * (j + 1) with alternating signs based on feature and hidden-unit indices. Initialize hidden-to-output weights using the same magnitude pattern with alternating signs. Initialize all biases to zero. Train using batch updates, then classify sigmoid outputs at threshold 0.5.

Constraints

  • 1 <= len(X) <= 500
  • 1 <= len(X[0]) <= 20
  • Every row has the same number of features
  • len(y) == len(X)
  • Each label in y is either 0 or 1
  • 1 <= hidden_size <= 20
  • 0 < learning_rate <= 1
  • 0 <= epochs <= 10000
  • Only Python lists and arithmetic may be used

Function Signature

def neural_network(X, y, hidden_size, learning_rate, epochs):
Your solutionPython 3
You need to log in / sign up to run or submit.
Run your code to see test output