Machine Learning is the act of analyzing large volumes of data using advanced data analytics tools and techniques. Big data, can be structured or unstructured based on their characteristics including the following:
- Metrics
- Events
- Logs
- Traces
Data is all around us — from our social media interactions, emails, traffic data or financial transactions. To make sense of all that data, we use advanced techniques and tools to extract unique insights, draw patterns and predict trends.
Some of the big data analytics techniques are:
- Machine learning is an aspect of artificial intelligence that allows computers to learn and imitate past experiences and human behavior. For it to work, a large volume of data has to be fed into the system to boost its accuracy level to near perfection.
- Predictive analysis, as the name implies, uses historical data and statistical algorithms to forecast future events.
- Deep Learning involves searching through large datasets to unearth patterns, make connections and extract insights.
- Natural Language Processing uses computer programs to understand and interpret human language, whether as text or voice.
In Machine Learning, you don’t only analyze data; you also develop prediction models, create visualizations, and communicate insights to stakeholders.
####################################################################################
The DIKW model suggests that data can be transformed into information by adding context and structure. This information can then be used to acquire knowledge, understanding, and insight about a particular subject.
Finally, wisdom is the highest level of the pyramid, representing the ability to use knowledge and experience to make sound decisions and judgments.
Hence, “D” – data, “I” – information, “K” – knowledge, and “W” – wisdom.
However, the model is overly simplistic and does not reflect how knowledge is created and shared or the many factors influencing how people understand and use information.
Some of the main reasons why the DIKW model is flawed include the following:
- Linear progression: The model assumes a linear progression from data to information to knowledge to wisdom, which is not always accurate in real-world scenarios.
- Lack of context: The model does not account for the context in which data, information, knowledge, and wisdom are used, which can significantly affect their meaning and value.
- Ignores emotions, subjectivity, and cognitive bias: The model does not consider the role of emotions, subjective human experience, and cognitive bias, which can also play a significant role in understanding and using data, information, knowledge, and wisdom.
- Lack of consideration for power and politics: The model does not consider the role of power and politics in shaping and limiting access to data, information, knowledge, and wisdom.
- Static nature: The model does not consider the dynamic nature of knowledge and wisdom and how they change over time and with new information.
Overall, the DIKW model is limited in its ability to fully capture the complexity and nuances of how information and knowledge are created, used, and understood in real-world contexts.
####################################################################################
- Dataset: A set of data examples, that contain features important to solving the problem.
- Features: Important pieces of data that help us understand a problem. These are fed in to a Machine Learning algorithm to help it learn.
- Model: The representation (internal model) of a phenomenon that a Machine Learning algorithm has learnt. It learns this from the data it is shown during training. The model is the output you get after training an algorithm. For example, a decision tree algorithm would be trained and produce a decision tree model.
- Data Collection: Collect the data that the algorithm will learn from.
- Data Preparation: Format and engineer the data into the optimal format, extracting important features and performing dimensionality reduction.
- Training: Also known as the fitting stage, this is where the Machine Learning algorithm actually learns by showing it the data that has been collected and prepared.
- Evaluation: Test the model to see how well it performs.
- Tuning: Fine tune the model to maximise it’s performance.
####################################################################################
-
🔭 I’m currently working on Learning Machine Learning
-
🌱 I’m currently learning Python and Jupyter using Numpy and Pandas
-
👨💻 All of my projects are available at https://github.com/netguru1966/netguru1966/projects?query=is%3Aopen
-
📝 I regularly write articles on https://www.splunk.com/en_us/blog
-
💬 Ask me about Machine Learning Toolkit (MLKT)
-
📫 How to reach me [email protected]
-
📄 Know about my experiences https://www.linkedin.com/in/netguru66/
-
⚡ Fun fact I worked as a Chicago Police Dept before Geeking Out
