#3 Ch3. Machine Learning — Deep Learning and Neural Networks
Deep learning fundamentals — from the perceptron to multi-layer networks (MLP), backpropagation, activation functions, and overfitting prevention with dropout and batch normalization.
We do not grow old as long as we strive to improve ourselves.
Deep learning fundamentals — from the perceptron to multi-layer networks (MLP), backpropagation, activation functions, and overfitting prevention with dropout and batch normalization.
WBS, scope creep, Critical Path Method (CPM), Earned Value Management (EVM) — managing the project triple constraint. PMP Chapter 3.
Python function writing (parameters, return values, lambdas), object-oriented programming (classes, inheritance, encapsulation), and practical bank account example.
NLP fundamentals — text preprocessing, Bag of Words, TF-IDF, word embeddings (Word2Vec), sentiment analysis pipeline, and text classification.
Risk identification, analysis, response strategies, quality planning/assurance/control, and quality tools. PMP Chapter 4.
Python file I/O (text, CSV, JSON), try-except exception handling, with statement, and a practical log file analysis example.
End-to-end ML project pipeline — EDA, cross-validation, hyperparameter tuning with Grid Search and Random Search, XGBoost/LightGBM, model serialization, and a churn-prediction case study.
Contract types (fixed price, cost reimbursable, T&M), change control process, Integrated Change Control. PMP Chapter 5.
Python essential standard library modules (os, datetime, random, collections), pip package management, and virtual environment setup.
Attention mechanism, Transformer architecture, BERT vs GPT, prompt engineering, RAG, fine-tuning with LoRA, AI ethics, and an ML career roadmap.
Ahoxy는 OIYO 패밀리가 되었습니다 👋 Ahoxy is now part of the OIYO family 👋
찾으시던 콘텐츠는 아래 사이트에서 계속 이용할 수 있어요. Everything you used lives on across these sites.