LESSON 31 OF 52 · CHAPTER 04
Numerical Kernels
variance, stddev, relu, sigmoid and tanh on numeric data
07-numerical-kernels.srp
bind samples = ints_to_vector(ints_range(-2, 5, 1));
print(variance(samples), stddev([3.0, 3.0]));
print(relu(samples));
print(sigmoid([-1000.0, 0.0, 1000.0]));
print(tanh([-1000.0, 0.0, 1000.0]));
stdout
2.0 0.0
[0.0, 0.0, 0.0, 1.0, 2.0]
[0.0, 0.5, 1.0]
[-1.0, 0.0, 1.0]
Write what you expect this program to print. Check prediction for a line-level hint without revealing the answer, or reveal the verified output when ready. This checks displayed text only; it does not run Scarp or save your input.
UNDERSTAND THE CODE
Explanation & practice
What this example teaches
variance, stddev, relu, sigmoid and tanh on numeric data
Expected behavior
2.0 0.0 and three vectors
Practice: Read the source before looking at the output. Predict the values and their order, then use the pinned compiler to execute this lesson and compare the exact fixture. Identify which operation produces the result.
संख्यात्मक फ़ंक्शन
variance संख्याओं का फैलाव और stddev मानक विचलन देता है। relu ऋणात्मक मानों को शून्य करता है; sigmoid और tanh संख्याओं को सीमित दायरों में बदलते हैं। यह फ़ंक्शन-स्तरीय गणना है, प्रशिक्षित न्यूरल नेटवर्क नहीं।
आउटपुट: पहले 2.0 0.0 और फिर तीन परिणाम वेक्टर: [0.0, 0.0, 0.0, 1.0, 2.0], [0.0, 0.5, 1.0], और [-1.0, 0.0, 1.0]।
अभ्यास: relu में -2.0 और -1.0 के लिए 0.0 क्यों आता है?
Explanations are sourced from the project's English chapter guide and हिन्दी अध्याय. The Scarp program and output are unchanged.
LEARNING PROGRESS
Keep your place
Mark this lesson complete when you are ready.
Only saved in this browser. No account or tracking.
TRY IT LOCALLY
Verify, then execute
Use the pinned compiler from the course root. Keep any imported _support files next to the source.
scarp verify examples/04-collections/07-numerical-kernels.srp
scarp exec examples/04-collections/07-numerical-kernels.srpThe website does not run code. Read the CLI guide ↗
Pinned compiler: Scarp v0.0.6-alpha.3
· ceff07d9014f. No simulated output.