Machine Learning (ML) Task

A Machine Learning (ML) Task is a learning task and automated task where a machine improves performance through iterative experiences with data.

• AKA: Automated Learning.
• Context:
  • Input:
    • Learning Data and optionally, a Testing Record Set to validate performance.
    • Includes several rounds of Information such as Learning Records.
  • Output:
    • A Decision Act, Prediction, or Model (e.g., Predictive Model or Cluster Model).
    • Can include an Inductive Argument or a set of actionable predictions.
  • It can be solved by a Machine Learning System implementing one or more Machine Learning Algorithms.
  • It can range from being a Supervised Machine Learning Task to an Unsupervised Learning Task.
  • It can range from a Batch ML Task to an Online Learning Task, including Reinforcement Learning Tasks.
  • It can also vary from Simple Input Learning Tasks to more Complex Input Learning Tasks.
  • Performance can be measured using metrics such as a Prediction Performance Measure or a Cost-Benefit Function.
  • It can be an Inductive Reasoning Task requiring inferences from unseen data based on a learning dataset.
  • It can range from being a Manual Learning Task to a fully Automated Learning Task.
  • It can also be part of an Active Learning Task where interaction plays a role.
  • It can be used in a variety of domains, forming the basis for a Machine Learning Discipline or contributing to a Machine Learning Application.
  • It can instantiate in Machine Learning Acts or benchmark tasks to evaluate systems.
  • ...
• Example(s):
  • A Machine Learning Classification Task to predict customer churn.
  • A Machine Learning Regression Task used to forecast housing prices.
  • A Deep Learning Task for image recognition.
  • A Reinforcement Learning Task used for robotic control.
  • A Predictive Function Learning Task for medical diagnostics.
  • A Machine Learning Benchmark Task such as the MNIST handwritten digit classification.
  • ...
• Counter-Example(s):
  • A Human Learning Task involving experiential learning not based on algorithms.
  • A Deductive Reasoning Task focusing on logical conclusions without data-driven improvements.
  • A Statistical Analysis Task that analyzes data but may not necessarily involve learning models.
  • An Exploration Task without the goal of predictive learning.
  • An Exploitation Task where decisions are made without further learning.
  • ...
• See: Data-Driven Prediction, Transfer Learning, Data Mining, Supervised Learning Task, Linguistically-Specified Learning Task

---

---

References

2018

• (Wikipedia, 2018) ⇒ https://en.wikipedia.org/wiki/Machine_learning Retrieved:2018-3-26.
  • Machine learning is a field of computer science that gives computer systems the ability to "learn" (i.e., progressively improve performance on a specific task) with data, without being explicitly programmed. The name Machine learning was coined in 1959 by Arthur Samuel. Evolved from the study of pattern recognition and computational learning theory in artificial intelligence, machine learning explores the study and construction of algorithms that can learn from and make predictions on data – such algorithms overcome following strictly static program instructions by making data-driven predictions or decisions, through building a model from sample inputs. Machine learning is employed in a range of computing tasks where designing and programming explicit algorithms with good performance is difficult or infeasible; example applications include email filtering, detection of network intruders or malicious insiders working towards a data breach, optical character recognition (OCR), learning to rank, and computer vision. Machine learning is closely related to (and often overlaps with) computational statistics, which also focuses on prediction-making through the use of computers. It has strong ties to mathematical optimization, which delivers methods, theory and application domains to the field. Machine learning is sometimes conflated with data mining, where the latter subfield focuses more on exploratory data analysis and is known as unsupervised learning. Machine learning can also be unsupervised and be used to learn and establish baseline behavioral profiles for various entities and then used to find meaningful anomalies. Within the field of data analytics, machine learning is a method used to devise complex models and algorithms that lend themselves to prediction; in commercial use, this is known as predictive analytics. These analytical models allow researchers, data scientists, engineers, and analysts to "produce reliable, repeatable decisions and results" and uncover "hidden insights" through learning from historical relationships and trends in the data. Effective machine learning is difficult because finding patterns is hard and often not enough training data are available; as a result, machine-learning programs often fail to deliver.

2017

• (Yufeng G, 2017) ⇒ Yufeng G (Aug 31, 2017) "The 7 Steps of Machine Learning". In: Medium - Towards Data Science Blog.
  • QUOTE: In particular, the formula for a straight line is $y=m*x+b$, where $x$ is the input, $m$ is the slope of that line, $b$ is the $y$-intercept, and $y$ is the value of the line at the position $x$. The values we have available to us for adjusting, or “training”, are $m$ and $b$. There is no other way to affect the position of the line, since the only other variables are $x$, our input, and $y$, our output.

    In machine learning, there are many $m$’s since there may be many features. The collection of these $m$ values is usually formed into a matrix, that we will denote $W$, for the “weights” matrix. Similarly for $b$, we arrange them together and call that the biases.

    The training process involves initializing some random values for $W$ and $b$ and attempting to predict the output with those values. As you might imagine, it does pretty poorly. But we can compare our model’s predictions with the output that it should produced, and adjust the values in $W$ and $b$ such that we will have more correct predictions.

    This process then repeats. Each iteration or cycle of updating the weights and biases is called one training “step”.

    

2006

• (Mitchell, 2006) ⇒ Tom M. Mitchell. (2006). “The Discipline of Machine Learning." Machine Learning Department technical report CMU-ML-06-108, Carnegie Mellon University.
  • QUOTE: … “How can we build computer systems that automatically improve with experience, and ...”

1998

• (Mitchell, 1998) ⇒ Tom Mitchell. (1998). “?"
  • QUOTE: Well-posed Learning Problem: A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.

---