Dasar-Dasar Kecerdasan Buatan Generatif dalam Python
Panduan komprehensif untuk memahami dan menerapkan Kecerdasan Buatan Generatif dan Model Bahasa Besar (LLM). Kursus ini membahas transisi dari dasar teoritis hingga pengembangan praktis berbasis Python, mencakup GAN, model difusi, transformer, fine-tuning, serta penempatan produksi.
Gambaran Umum Kursus
📚 Ringkasan Konten
Panduan komprehensif untuk memahami dan menerapkan Kecerdasan Buatan Generatif dan Model Bahasa Besar (LLM). Kursus ini membahas transisi dari fondasi teoretis hingga pengembangan praktis berbasis Python, mencakup GAN, model difusi, transformer, fine-tuning, serta penempatan produksi.
Kelola prinsip dasar dan aplikasi praktis LLM modern serta teknik generatif dengan Python.
Penulis: Carlos Rodriguez
Ucapan Terima Kasih: Ucapan khusus kepada istri penulis, Jill, orang tua penulis, serta para reviewer teknis Morgan Boyce, Eric Rui, dan Samira Shaikh (penulis kata pengantar).
🎯 Tujuan Pembelajaran
- Membedakan antara paradigma pembelajaran mesin klasik (diskriminatif) dan model AI generatif.
- Mengidentifikasi arsitektur dasar AI generatif, termasuk GAN, model difusi, dan Transformer.
- Menerangkan peran dan evolusi Model Bahasa Besar (LLM) dalam lingkup kecerdasan buatan yang lebih luas.
- Membedakan fitur unik dan paradigma arsitektur GAN, model difusi, dan transformer.
- Menganalisis kemajuan dan keterbatasan setiap jenis model, termasuk masalah spesifik seperti kolaps mode atau kecepatan sampling.
- Menerapkan pipeline Stable Diffusion dan mengevaluasi hasil generasi menggunakan logits dan probabilitas berbasis CLIP.
- Melacak evolusi NLP dari metode berbasis hitungan awal dan RNN hingga representasi terdistribusi modern dan pembelajaran transfer.
- Menerangkan mekanisme teknis Multi-head Attention (MHA), Self-attention, Masking, dan Jaringan Feed-Forward (FFN).
- Menerapkan arsitektur model Transformer lengkap, termasuk tokenisasi data, encoding posisi, dan fungsi pelatihan/inferensi.
- Menghubungkan fitur prototipe (misalnya Google Colab) ke lingkungan siap produksi menggunakan Docker dan VS Code.
Pelajaran 共 7 课时 · 预计 21.0h
Pelajaran
Lesson
This lesson explores the concept of the technological Singularity and the exponential growth of AI, while establishing the fundamental distinction between discriminative models that classify data and generative models that synthesize it. Students will learn to analyze the synergy between compute, data, and algorithmic efficiency, as well as the mathematical foundations of probabilistic modeling in high-dimensional spaces.
This lesson explores the three core pillars of generative AI—GANs, diffusion models, and transformers—by analyzing their unique mathematical strategies and architectural trade-offs. Students will learn to differentiate these models based on their training stability, computational efficiency, and specific applications in multimodal synthesis.
This lesson explores the evolution of Natural Language Processing from sparse, count-based methods like TF-IDF to dense, distributed vector representations and recurrent neural architectures. It examines the limitations of RNNs and LSTMs, such as the vanishing gradient problem and the Seq2Seq bottleneck, while establishing the mathematical foundations of the Transformer architecture and self-attention mechanisms.
AI030: Production Engineering and Responsible AI Deployment (Lesson 4) explores the transition from experimental prototyping in notebooks to robust, scalable production systems. Students will learn to implement CI/CD pipelines, ensure model reliability through automated testing, and integrate fairness monitoring to meet ethical and regulatory standards.
This lesson explores the spectrum of model adaptation, comparing the computational efficiency of In-Context Learning with the specialized performance and stability of Parameter-Efficient Fine-Tuning (PEFT) and full fine-tuning. Students will learn to navigate the trade-offs between hardware constraints and model alignment, with a focus on implementing techniques like LoRA to optimize performance in resource-limited environments.
This lesson explores the necessity of domain adaptation for general-purpose LLMs, focusing on techniques like continued pre-training and fine-tuning to align model knowledge with specialized fields. Students will learn to implement parameter-efficient methods like LoRA and develop evaluation frameworks to ensure linguistic accuracy in high-stakes professional environments.
This lesson explores the paradigm shift from resource-heavy model fine-tuning to efficient prompt-based inference and in-context learning. Students will learn to master advanced prompting techniques, such as persona-based conditioning and Chain-of-Thought, to optimize model performance and maintain factual consistency.