SUMMARY: The purpose of this project is to construct a predictive model using various machine learning algorithms and to document the end-to-end steps using a template. The Superconductor Critical Temperature dataset is a regression situation where we are trying to predict the value of a continuous variable.

INTRODUCTION: The research team wishes to create a statistical model for predicting the superconducting critical temperature based on the features extracted from the superconductor’s chemical formula. The model seeks to examine the features that can contribute the most to the model’s predictive accuracy.

From iteration Take1, we constructed and tuned machine learning models for this dataset using TensorFlow with five layers. We also observed the best result that we could obtain using the tuned models with the validation and test datasets.

From iteration Take2, we constructed and tuned machine learning models for this dataset using TensorFlow with dropout layers. We also observed the best result that we could obtain using the tuned models with the validation and test datasets.

In this Take3 iteration, we will construct and tune a TensorFlow model with five layers using the additional material attributes available for modeling. Furthermore, we will apply the tuned model to a test dataset and observe the best result that we can obtain from the model.

ANALYSIS: From iteration Take1, the baseline performance of the TensorFlow algorithm achieved an RMSE benchmark of 11.109. After a series of tuning trials, the TensorFlow model processed the validation dataset with an RMSE score of 10.564. When we applied the TensorFlow model to the previously unseen test dataset, we obtained an RMSE score of 10.540.

From iteration Take2, the baseline performance of the TensorFlow algorithm achieved an RMSE benchmark of 10.580. After a series of tuning trials, the TensorFlow model processed the validation dataset with an RMSE score of 10.905. When we applied the TensorFlow model to the previously unseen test dataset, we obtained an RMSE score of 10.885.

In this Take3 iteration, the baseline performance of the TensorFlow algorithm achieved an RMSE benchmark of 12.298. After a series of tuning trials, the TensorFlow model processed the validation dataset with an RMSE score of 10.299. When we applied the TensorFlow model to the previously unseen test dataset, we obtained an RMSE score of 10.144.

CONCLUSION: In this iteration, the TensorFlow model appeared to be a suitable algorithm for modeling this dataset. We should consider using the algorithm for further modeling.

Dataset Used: Superconductivity Data Set

Dataset ML Model: Regression with numerical attributes

Dataset Reference: https://archive.ics.uci.edu/ml/datasets/Superconductivty+Data

One potential source of performance benchmarks: https://doi.org/10.1016/j.commatsci.2018.07.052

The HTML formatted report can be found here on GitHub.

]]>The purpose of this modeling exercise is to construct an end-to-end template for solving machine learning problems. This Python script will adapt Dr. Jason Brownlee’s blog post on this topic and build a robust template for solving similar problems.

Version 1 of the AutoKeras binary classification template contains structures and features that are like the Scikit-Learn templates. I pull together this template to take a machine learning exercise from beginning to end.

You will find the Python templates on the Machine Learning Project Templates page.

]]>SUMMARY: The purpose of this project is to construct a predictive model using various machine learning algorithms and to document the end-to-end steps using a template. The Superconductor Critical Temperature dataset is a regression situation where we are trying to predict the value of a continuous variable.

INTRODUCTION: The research team wishes to create a statistical model for predicting the superconducting critical temperature based on the features extracted from the superconductor’s chemical formula. The model seeks to examine the features that can contribute the most to the model’s predictive accuracy.

From iteration Take1, we constructed and tuned machine learning models for this dataset using TensorFlow with five layers. We also observed the best result that we could obtain using the tuned models with the validation and test datasets.

In this Take2 iteration, we will construct and tune machine learning models for this dataset using TensorFlow with dropout layers. We will observe the best result that we can obtain using the tuned models with the validation and test datasets.

ANALYSIS: From iteration Take1, the baseline performance of the TensorFlow algorithm achieved an RMSE benchmark of 11.109. After a series of tuning trials, the TensorFlow model processed the validation dataset with an RMSE score of 10.564. When we applied the TensorFlow model to the previously unseen test dataset, we obtained an RMSE score of 10.540.

In this Take2 iteration, the baseline performance of the TensorFlow algorithm achieved an RMSE benchmark of 10.580. After a series of tuning trials, the TensorFlow model processed the validation dataset with an RMSE score of 10.905. When we applied the TensorFlow model to the previously unseen test dataset, we obtained an RMSE score of 10.885.

CONCLUSION: In this iteration, the TensorFlow model with the dropout layers did not appear to have a noticeable effect on the modeling of this dataset. However, we still should consider using the algorithm for further modeling.

Dataset Used: Superconductivity Data Set

Dataset ML Model: Regression with numerical attributes

Dataset Reference: https://archive.ics.uci.edu/ml/datasets/Superconductivty+Data

One potential source of performance benchmarks: https://doi.org/10.1016/j.commatsci.2018.07.052

The HTML formatted report can be found here on GitHub.

]]>SUMMARY: The purpose of this project is to construct a predictive model using various machine learning algorithms and to document the end-to-end steps using a template. The Superconductor Critical Temperature dataset is a regression situation where we are trying to predict the value of a continuous variable.

INTRODUCTION: The research team wishes to create a statistical model for predicting the superconducting critical temperature based on the features extracted from the superconductor’s chemical formula. The model seeks to examine the features that can contribute the most to the model’s predictive accuracy.

In this Take1 iteration, we will construct and tune machine learning models for this dataset using TensorFlow with five layers. We will observe the best result that we can obtain using the tuned models with the validation and test datasets.

ANALYSIS: The baseline performance of the TensorFlow algorithm achieved an RMSE benchmark of 11.109. After a series of tuning trials, the TensorFlow model processed the validation dataset with an RMSE score of 10.564. When we applied the TensorFlow model to the previously unseen test dataset, we obtained an RMSE score of 10.540.

CONCLUSION: In this iteration, the TensorFlow model appeared to be a suitable algorithm for modeling this dataset. We should consider using the algorithm for further modeling.

Dataset Used: Superconductivity Data Set

Dataset ML Model: Regression with numerical attributes

Dataset Reference: https://archive.ics.uci.edu/ml/datasets/Superconductivty+Data

One potential source of performance benchmarks: https://doi.org/10.1016/j.commatsci.2018.07.052

The HTML formatted report can be found here on GitHub.

]]>In this podcast, Seth discusses the states and the differences between industrialism and capitalism. People sometimes use the words industrialism and capitalism interchangeably. Both are seen as an invisible force that has shaped our culture and our way of life.

Industrialism is a process that craves productivity because lower price wins. The productivity that results in lower prices come from cheaper labor with fewer protections. Industrialism, therefore, demands that everyone in the system feels obligated to go against their morals because productivity is, in many cases, a race to the bottom.

Throughout our industrial age, there are many examples of industrialism, leading us to cultural changes that were dehumanizing. One example is the rise of the cotton industry, coupled with the need for cheap labor. For a long time, the cotton industry relied on slavery as the primary source of cheap labor and productivity.

Capitalism is about free markets and choice. Markets are listening instruments, and they exist to figure out what people want and to prioritize what they get. When we have freedom, it can be the fuel for dignity. In truly free markets, slavery would be impossible because people would have the right and choices to make about their labor.

Industrialism, on the other hand, is its own master. Industrialism is also about power, power over people, markets, and systems. Because it has created surplus and prizes along the way, people have permitted industrialism to run through our culture. In many places, the relentless race to create something ever cheaper has led to the cost to the environment or the people.

Industrialism also seeks monopoly because monopoly is the best way to gain power. While there are few real monopolies around us, we have industrial organizations that practice monopolistic conspiracies. These are oligopolies, groups of corporations and individuals, working together to create less choice.

We call something a conspiracy when people or organizations are cooperating in a way that hurts others. Conspiracies that promote monopoly cab do damage, and those business practices are not secretive. We have many examples of industrial organizations conducting productivity-enhancing practices at the expense of the people and our culture.

Furthermore, computers and machines are becoming the tools used by the oligopolies that seek to maximize their return while giving people less choice. Machines changed everything about industrialism because machines are tireless. Machines do not complain, and they do not bring the baggage of morality with them.

Machines also hastened the race to monopoly because machines can be built and improved to create insulation for the people who do have the machines. With network connectivity, machines also amplify the network effect. The network effect means that successful leaders can become even more potent because they can achieve lock-in. Such lock-in also leads to more profit, more coercion, and more conspiracy.

Industrialism is not the same as capitalism. Industrialism is the repeated process of getting something cheaper and faster. Eventually, industrialism requires coercion by pushing people running the industry not to take responsibility for what they are doing.

Capitalism is about discovering market needs and filling them. It works best when people take responsibility for what they do. We have an opportunity to create boundaries for both industrialism and capitalism, and we can make boundaries that benefit all of us.

Most importantly, we can make both concepts work to our advantage by creating a positive culture. We can create a culture that is based on dignity and choices over the long term.

]]>人們不會僱用您，不會向您購買或推薦您，只因為您的平均水平很全面但並不高。

他們這樣做是因為您在某些方面出類拔萃。

如果您想投入精力以使其更加出色，你會該往那個方向投入？

]]>From previous iterations, we constructed and tuned several classic machine learning models using the Scikit-Learn library. We also observed the best results that we could obtain from the models.

From iteration Take1, we constructed and tuned an XGBoost model. Furthermore, we applied the XGBoost model to a test dataset and observed the best result that we could obtain from the model.

In this Take2 iteration, we will construct and tune an XGBoost model using the additional material attributes available for modeling. Furthermore, we will apply the XGBoost model to a test dataset and observe the best result that we can obtain from the model.

ANALYSIS: From previous iterations, the Extra Trees model turned in the best overall result and achieved an RMSE metric of 9.56. By using the optimized parameters, the Extra Trees algorithm processed the test dataset with an RMSE of 9.32.

From iteration Take1, the baseline performance of the XGBoost algorithm achieved an RMSE benchmark of 12.88. After a series of tuning trials, the XGBoost model processed the validation dataset with an RMSE score of 9.88. When we applied the XGBoost model to the previously unseen test dataset, we obtained an RMSE score of 9.06.

In this Take2 iteration, the baseline performance of the XGBoost algorithm achieved an RMSE benchmark of 12.54. After a series of tuning trials, the XGBoost model processed the validation dataset with an RMSE score of 9.58. When we applied the XGBoost model to the previously unseen test dataset, we obtained an RMSE score of 8.94.

CONCLUSION: In this iteration, the additional material attributes improved the XGBoost model further for modeling this dataset. We should consider using the algorithm for further modeling.

Dataset Used: Superconductivity Data Set

Dataset ML Model: Regression with numerical attributes

Dataset Reference: https://archive.ics.uci.edu/ml/datasets/Superconductivty+Data

One potential source of performance benchmarks: https://doi.org/10.1016/j.commatsci.2018.07.052

The HTML formatted report can be found here on GitHub.

]]>From previous iterations, we constructed and tuned several classic machine learning models using the Scikit-Learn library. We also observed the best results that we could obtain from the models.

In this Take1 iteration, we will construct and tune an XGBoost model. Furthermore, we will apply the XGBoost model to a test dataset and observe the best result that we can obtain from the model.

ANALYSIS: From previous iterations, the Extra Trees model turned in the best overall result and achieved an RMSE metric of 9.56. By using the optimized parameters, the Extra Trees algorithm processed the test dataset with an RMSE of 9.32.

In this Take1 iteration, the baseline performance of the XGBoost algorithm achieved an RMSE benchmark of 12.88. After a series of tuning trials, the XGBoost model processed the validation dataset with an RMSE score of 9.88. When we applied the XGBoost model to the previously unseen test dataset, we obtained an RMSE score of 9.06.

CONCLUSION: In this iteration, the XGBoost model appeared to be a suitable algorithm for modeling this dataset. We should consider using the algorithm for further modeling.

Dataset Used: Superconductivity Data Set

Dataset ML Model: Regression with numerical attributes

Dataset Reference: https://archive.ics.uci.edu/ml/datasets/Superconductivty+Data

One potential source of performance benchmarks: https://doi.org/10.1016/j.commatsci.2018.07.052

The HTML formatted report can be found here on GitHub.

]]>Thanks to Dr. Jason Brownlee’s suggestions on creating a machine learning template, I have pulled together a set of project templates that I use to experiment with modeling ML problems using Python and XGBoost.

Version 1 of the XGBoost templates contains structures and features that are similar to the Scikit-Learn templates. The XGBoost templates were designed to take a machine learning modeling exercise from beginning to end.

You will find the Python templates on the Machine Learning Project Templates page.

]]>Thanks to Dr. Jason Brownlee’s suggestions on creating a machine learning template, I have pulled together a set of project templates that I use to experiment with modeling ML problems using Python and Scikit-Learn.

Version 15 of the Scikit-Learn templates contains minor adjustments and corrections to the prevision version of the model. The updated templates include the following:

- Introduced example code segments for splitting one original datasets into training, validation, and test datasets
- Introduced example code segments for pre-processing and scaling data with Scikit-Learn’s pipeline

You will find the Python templates on the Machine Learning Project Templates page.

]]>