Mathematics For Machine Learning Course
What will I learn?
ናይ ንግዲ ኢንተለጀንስ ክእለትካ/ክእለትኪ ኣብ'ዚ ትምህርቲ ሒሳብ ንማሽን መምሃሪ ብምውሳድ ኣዕብዮ/ኣዕብይዮ። ዳታ ምድህሳስ ብምክያድ፡ እንታይ ከምዘለዎም ንምፍላጥን (outliers) ከምኡ'ውን ዘየለዉ ነገራት ከመይ ጌርካ ከም ትቆጻጸሮ/ትቆጻጸሪ ተምሃር። ቅድመ ምድላው ዳታን፡ መምዘንን ከመይ ጌርካ ኸም እትሰርሖን (normalization)፡ ከምኡ'ውን ነቶም ዘለዉ ከመይ ጌርካ ኸም እትቆጻጸሮም/ትቆጻጸሪዮም (outlier treatment) ተምሃር፡ እዚ ድማ ሞዴልካ ዝያዳ ትኽክል ክኸውን ይሕግዝ። ነቶም ንግዜ ተኸታታሊ ዝኾኑ ማሽን መምሃሪ ኣልጎሪዝምታት ተምሃር፡ ከም ናይ ውሳኔታት ኣግራብን (decision trees) ኣሪማን (ARIMA)። ኣብ ምህንድስና መለለዪታት (feature engineering)፡ ስልቲታት ምምሕያሽን (optimization techniques)፡ ከምኡ'ውን ሞዴል ከመይ ከም እትገምግም/ትገምግሚ (model evaluation) ክእለትካ/ክእለትኪ ኣመሓይሽ/ኣመሓይሺ። እዚ ኮርስ'ዚ ኣብ ናይ ሓቂ ዓለም ንትጥቀመሎም ግብራዊን ጥዑይን ክእለታት የዕጥቀካ/የዕጥቀኪ።
Apoia's Unique Features
Develop skills
Enhance your practical skills outlined below
መዋቅር ዳታ ምልላይ (Master data structures)፡ ነቲ ዝተሓላለኸ ዳታታት ብትኽክል ተንትኖን ተረድኦን።
ንዘይተለምዱ ነገራት ምፍላጥ (Detect outliers)፡ ንትኽክለኛነትን ምትእምማንን ናይ ዳታ ንምዕባይ፡ እንታይ ከምዘሎ ምፍላጥ።
ንግዜ ተኸታታሊ ሞዴላት ተጠቃቀም (Apply time series models)፡ ኣሪማን (ARIMA) ከምኡ'ውን ኤል-ኤስ-ቲ-ኤም (LSTM) ንግቡጽ ትንበያ ተጠቐም።
ኣልጎሪዝምታት ኣመሓይሽ (Optimize algorithms)፡ ንውጽኢታዊ ስልጠና ሞዴል፡ ናይ ደረጃ ምውራድ ስልቲ ተጠቐም (Implement gradient descent).
መለለዪታት ምህንድስና (Engineer features)፡ ንውጽኢት ሞዴል ንምምሕያሽ፡ ናይ ብዙሕነት መለለዪታት ፍጠር (Create polynomial features).
Suggested summary
Workload: between 4 and 360 hours
Before starting, you can change chapters and workload.
- Choose which chapter to start with
- Add or remove chapters
- Increase or decrease the course workload
Examples of chapters you can add
You will be able to generate more chapters like the examples below
This is a free course, focused on personal and professional development. It is not equivalent to a technical, undergraduate, or postgraduate course, but offers practical and relevant knowledge for your professional journey.