Category: machine learning

Rule-base AI vs ML

Posted on by lechuck park

The primary purpose of this image is to highlight the complementary nature of Rule-base AI and Machine Learning (ML), demonstrating the need to integrate these two approaches.

Rule-base AI (Top):

  • Emphasizes the importance of fundamental and ethical approaches
  • Designing strict rules based on human expertise and logical thinking
  • Providing core principles and ethical frameworks

Machine Learning AI (Bottom):

  • Highlighting scalability and innovation through data-driven learning
  • Ability to recognize complex patterns and adaptive learning
  • Potential for generating new insights and solutions

Hybrid Approach:

  • Combining the strengths of both approaches
  • Maintaining fundamental principles and ethical standards
  • Simultaneously achieving innovation and scalability through data-driven learning

The image illustrates the complementary nature of Rule-base AI and Machine Learning (ML). Rule-base AI represents precise, human-crafted logic with limited applicability, while ML offers flexibility and innovation through data-driven learning. The key message is that a hybrid approach combining the fundamental ethical principles of rule-based systems with the scalable, adaptive capabilities of machine learning can create more robust and intelligent AI solutions.

with Claude

CFD & AI/ML

Posted on by lechuck park

CFD (Computational Fluid Dynamics) – Deductive Approach [At Installation]

  • Data Characteristics
    • Configuration Data
    • Physical Information
    • Static Meta Data
  • Features
    • Complex data configuration
    • Predefined formula usage
    • Result: Fixed and limited
    • Stable from engineering perspective

AI/ML – Inductive Approach [During Operation]

  • Data Characteristics
    • Metric Data
    • IoT Sensing Data
    • Variable Data
  • Features
    • Data-driven formula generation
    • Continuous learning and verification
    • Result: Flexible but partially unexplainable
    • High real-time adaptability

Comprehensive Comparison

Harmonious integration of both approaches is key to future digital twin technologies

CFD: Precise but rigid modeling

AI/ML: Adaptive but complex modeling

The key insight here is that both CFD and AI/ML approaches have unique strengths. CFD provides a rigorous, physics-based model with predefined formulas, while AI/ML offers dynamic, adaptive learning capabilities. The future of digital twin technology likely lies in finding an optimal balance between these two methodologies, leveraging the precision of CFD with the flexibility of machine learning.

With Claude

AI persona

Posted on by lechuck park

with a Claude’s Help
This image shows a diagram illustrating the process flow of an AI Persona system. It demonstrates five stages progressing from left to right:

  1. Life Logging:
  • Records daily activities such as listening to music and conversations
  • Data appears to be collected through mobile devices
  1. Digitization:
  • Converting and processing collected data into digital format
  • Shown with settings and document icons
  1. AI Learning:
  • Stage where AI learns from the digitized data
  • Represented by a circuit network icon
  1. AI Agent:
  • Formation of an AI agent based on learned data
  • Symbolized by an icon showing the integration of AI and human elements
  1. Digital World:
  • Final stage where the AI persona operates in the digital world
  • Represented by a global network icon

The diagram effectively illustrates the complete process of how human activities and characteristics are digitized, transformed into AI, and ultimately utilized in the digital world. Each step is clearly labeled and represented with relevant icons that help visualize the transformation from real-world data to digital AI persona.

The image appears to be part of a technical presentation or documentation, as indicated by the email address visible in the top right corner. The flow is presented in a clear, linear fashion with connecting arrows showing the progression between each stage. C

Normalization, Standardization, Regularization

Posted on by lechuck park

with a claude’s help
This image is a diagram explaining three important concepts in machine learning: Normalization, Standardization, and Regularization.

The diagram is structured as follows:

  1. On the left side, there are document icons representing Input Data, and on the right side, there is a neural network structure representing the Learning Model.

Each concept is explained:

  1. Normalization:
  • Process of adjusting data range to [0 to 1] or [-1 to 1]
  • Scales data to fit within a specific range
  1. Standardization:
  • Process of adjusting data distribution
  • Transforms data to have an average of 0 and standard deviation of 0
  1. Regularization:
  • Controls model complexity and prevents overfitting
  • Prevents the model from becoming too closely fitted to the training data

These techniques are essential preprocessing and training steps for improving machine learning model performance and ensuring stable learning.

These techniques are fundamental in machine learning as they help in:

Enhancing overall model performance

Making data consistent and comparable

Improving model training efficiency

Preventing model overfitting

Prophet

Posted on by lechuck park

With a Claude’s help
The image appears to be a diagram or concept map that explains the components of the Prophet forecasting model, which is a popular time series forecasting library in Python. Here’s a breakdown of the key elements:

The diagram also shows different types of trend, seasonality, and holiday effects that the Prophet model can handle.

The main function is y(t), which represents the time series data that needs to be forecasted.

y(t) is composed of four additive components:

g(t): The trend component, which represents the long-term linear or piecewise linear growth trend in the data.

s(t): The seasonality component, which captures yearly and weekly seasonality patterns in the data.

h(t): The holiday effects component, which accounts for the impact of holidays or special events on the data.

e: The error term, which represents noise and uncertainty in the data.

The Era of True Artificial Intelligence: Bridging Human and Machine Learning  

Posted on by lechuck park

AI has now reached a level that can truly be called Artificial Intelligence. This is especially evident in the era of Machine Learning (ML). Humans learn through experiences—essentially data—and make judgments and take actions based on them. These actions are not always perfect or correct, but through continuous learning and experience, they strive for better outcomes, which inherently reflects a probabilistic and statistical perspective.

Similarly, ML learns from massive datasets to identify rules and minimize errors. However, it cannot achieve 100% perfection because it cannot learn all possible data, which is essentially infinite. Despite this, recent advancements in infrastructure and access to vast amounts of data have enabled AI to reach accuracy levels of 90% to 99.99%, appearing almost perfect.

Nevertheless, there still remains the elusive 0.00…1% of uncertainty, stemming from the fundamental limitation of incomplete data learning. Ultimately, AI is not so different from humans in how it learns and makes probabilistic decisions. For this reason, we can truly call it Artificial Intelligence.

Time Series Prediction : 3 types

Posted on by lechuck park

with a Claude’s help
This image provides an overview of different time series prediction methods, including their characteristics and applications. The key points are:

ARIMA (Autoregressive Integrated Moving Average):

  • Suitable for linear, stable datasets where interpretability is important
  • Can be used for short-term stock price prediction and monthly energy consumption forecasting

Prophet:

  • A quick and simple forecasting method with clear seasonality and trend
  • Suitable for social media traffic and retail sales predictions

LSTM (Long Short-Term Memory):

  • Suitable for dealing with nonlinear, complex, large-scale, feature-rich datasets
  • Can be used for sensor data anomaly detection, weather forecasting, and long-term financial market prediction

Application in a data center context:

  • ARIMA: Can be used to predict short-term changes in server room temperature and power consumption
  • Prophet: Can be used to forecast daily, weekly, and monthly power usage patterns
  • LSTM: Can be used to analyze complex sensor data patterns and make long-term predictions

Utilizing these prediction models can contribute to energy efficiency improvements and proactive maintenance in data centers. When selecting a prediction method, one should consider the characteristics of the data and the specific forecasting requirements.