LESSON 52 OF 52 · CHAPTER 06
Matrix Probabilities
Equal-score softmax and categorical-loss tolerance check
11-matrix-probabilities.srp
bind weights = tile([1.0, 0.0, 0.0, 1.0], 2, 2);
bind scores = matvec(weights, [0.0, 0.0]);
print(softmax(scores));
bind loss = crossentropy(scores, 1);
print(loss > 0.6931 and loss < 0.6932);
stdout
[0.5, 0.5]
true
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
Equal-score softmax and categorical-loss tolerance check
Expected behavior
[0.5, 0.5], then true
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.
स्कोर से संख्यात्मक संभावनाएँ
पहचान मैट्रिक्स (tile) और शून्य फीचर से दोनों वर्गों के बराबर स्कोर मिलते हैं। softmax दोनों को 0.5 देता है। crossentropy(scores, 1) का परिणाम 0.6931 से 0.6932 के बीच है—इसलिए प्रोग्राम true दिखाता है। इससे कोई प्रशिक्षित मॉडल या स्वचालित ग्रेडिएंट प्रणाली सिद्ध नहीं होती।
आउटपुट: पहली लाइन [0.5, 0.5], दूसरी true।
अभ्यास: दो बराबर स्कोर से दो बराबर संभावनाएँ क्यों बनती हैं, और लॉस को सटीक बराबरी के बजाय दायरे में क्यों जाँचा गया?
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/06-ai-foundations/11-matrix-probabilities.srp
scarp exec examples/06-ai-foundations/11-matrix-probabilities.srpThe website does not run code. Read the CLI guide ↗
CHAPTER 06 · LAST LESSON
Ready for your next step? · आगे क्या सीखें?
This is the final example in this chapter. Try its verified coding lab before moving on. Your lesson progress changes only when you mark a lesson complete.
Pinned compiler: Scarp v0.0.6-alpha.3
· ceff07d9014f. No simulated output.