株式会社PROMPT– Author –
-
[AI from Scratch] Episode 215: Introduction to Pandas — Basics of the Data Manipulation Library
Recap and Today's Theme Hello! In the previous episode, we explored the basics of NumPy, a library for high-speed numerical computation in Python. NumPy enables efficient operations like array manipulation, matrix calculations, and stati... -
[AI from Scratch] Episode 216: Reading and Saving Data — Handling CSV, Excel, JSON Files
Recap and Today's Theme Hello! In the previous episode, we learned the basics of the Pandas library for data manipulation. We explored how Pandas makes it easy to work with data frames for tasks like filtering, aggregation, and modificat... -
[AI from Scratch] Episode 213: How to Use Jupyter Notebook — Basic Operations of an Interactive Development Tool
Recap and Today's Theme Hello! In the previous episode, we covered the setup of Python development environments using Anaconda, making it easy to create virtual environments and manage Python and libraries efficiently. Today, we will lea... -
[AI from Scratch] Episode 214: Introduction to NumPy — Numerical Computation Library
Recap and Today's Theme Hello! In the previous episode, we explored the basic operations of Jupyter Notebook. By using Jupyter Notebook, you can run Python code interactively and immediately check the results, making data analysis and AI... -
[AI from Scratch] Episode 212: Installing and Setting Up Anaconda — Building a Development Environment
Recap and Today's Theme Hello! In the previous episode, we explored the basics of Python, covering essential knowledge for AI development such as Python syntax, data types, lists, conditional statements, loops, and functions. Today, we w... -
[AI from Scratch] Episode 211: Python Basics — An Introduction to Python for AI Development
Recap and Today's Theme Hello! In the previous episode, we reviewed and conducted a knowledge check for Chapter 7, reflecting on and deepening our understanding of the concepts we covered. Today, we begin Chapter 8 and explore the basics... -
[AI from Scratch] Episode 209: Neural Radiance Fields (NeRF)
Recap: Diffusion Models In the previous episode, we discussed Diffusion Models, explaining their mechanisms, applications, and differences from other generative models like GANs and VAEs. Diffusion models are gaining attention for their ... -
[AI from Scratch] Episode 208: Diffusion Models — An Introduction to Diffusion Models
Recap: Challenges and Limitations of Generative Models In the previous episode, we explored the challenges and limitations of generative models, including quality issues, computational costs, and ethical concerns. While generative models... -
[AI from Scratch] Episode 207: Challenges and Limitations of Generative Models
Recap: Applications of Generative Models In the previous episode, we explored various applications of generative models such as image generation, text generation, and speech synthesis. These technologies have broad applications, ranging ... -
[AI from Scratch] Episode 206: Applications of Generative Models — Image Generation, Text Generation, and Speech Synthesis
Recap: Model Safety and Filtering In the previous episode, we explored filtering techniques to ensure the safety of AI models. Methods such as the blacklist approach, NLP filtering, and Human-in-the-Loop (HITL) were discussed to prevent ... -
[AI from Scratch] Episode 205: Model Safety and Filtering — Preventing Inappropriate Outputs
Recap: Prompt Tuning In the previous episode, we learned about prompt tuning, a technique to optimize prompts for eliciting desired outputs from pre-trained models. Designing prompts effectively is crucial for enhancing model accuracy an... -
[AI from Scratch] Episode 203: Large-Scale Pre-Trained Models — Advantages and Applications of Pre-Trained Models
Recap: Applications of Self-Supervised Learning In the previous episode, we discussed the applications of self-supervised learning, a method that learns features from unlabeled data. This approach has proven valuable in fields such as na... -
[AI from Scratch] Episode 204: Prompt Tuning — Optimizing Prompts to Enhance Model Performance
Recap: Large-Scale Pre-Trained Models In the previous episode, we discussed large-scale pre-trained models, which are models trained on massive datasets that exhibit high performance when their general features are applied to specific ta... -
[AI from Scratch] Episode 202: Applications of Self-Supervised Learning — Learning from Unlabeled Data
Recap: Evaluation Metrics for Speech Generation In the previous episode, we explained how to evaluate the quality of speech generation using metrics like PESQ and STOI for objective evaluation and MOS for subjective evaluation. These met... -
[AI from Scratch] Episode 201: Evaluation Metrics for Speech Generation — PESQ, STOI, and More
Recap: Tacotron In the previous episode, we explained Tacotron, a model that converts text into speech, widely used in applications such as voice assistants and narration generation. Especially with Tacotron 2, the quality of the generat...
