AI News, Why is machine learning 'hard'?
- On Tuesday, June 5, 2018
- By Read More
Why is machine learning 'hard'?
There have been tremendous advances made in making machine learning more accessible over the past few years.
Online courses have emerged, well-written textbooks have gathered cutting edge research into an easier to digest format and countless frameworks have emerged to abstract the low level messiness associated with building machine learning systems.
In some cases these advancements have made it possible to drop an existing model into your application with a basic understanding of how the algorithm works and a few lines of code.
Machine learning remains a hard problem when implementing existing algorithms and models to work well for your new application.
This difficulty is often not due to math - because of the aforementioned frameworks machine learning implementations do not require intense mathematics.
Regular software engineering requires awareness of the trade offs of competing frameworks, tools and techniques and judicious design decisions.
In standard software engineering when you craft a solution to a problem and something doesn’t work as expected in most cases you have two dimensions along which things could have gone wrong: algorithmic or implementation issues.
The debugging process then becomes a matter of combining the signals you have about the bug (compiler error messages, program outputs etc.) with your intuition on where the problem might be.
The reason this is 'exponentially' harder is because if there are n possible ways things could go wrong in one dimension there are n x n ways things could go wrong in 2D and n x n x n x n ways things can go wrong in 4D.
For example, signals that are particularly useful are plots of your loss function on your training and test sets, actual output from your algorithm on your development data set and summary statistics of the intermediate computations in your algorithm.
This is a key skill that you develop as you continue to build out machine learning projects: you begin to associate certain behavior signals with where the problem likely is in your debugging space.
After much trial and error I eventually learned that this is often the case of a training set that has not been correctly randomized (it was an implementation issue that looked like a data issue) and is a problem when you are using stochastic gradient algorithms that process the data in small batches.
- On Tuesday, March 26, 2019
Python Machine Learning Tutorial | Machine Learning Algorithms | Python Training | Edureka
Python Training : ) This Edureka Python tutorial (Python Tutorial Blog: gives an introduction to Machine .
Lecture 6 | Training Neural Networks I
In Lecture 6 we discuss many practical issues for training modern neural networks. We discuss different activation functions, the importance of data ...
Visualizing a Decision Tree - Machine Learning Recipes #2
Last episode, we treated our Decision Tree as a blackbox. In this episode, we'll build one on a real dataset, add code to visualize it, and practice reading it - so ...
Lecture 3 | Loss Functions and Optimization
Lecture 3 continues our discussion of linear classifiers. We introduce the idea of a loss function to quantify our unhappiness with a model's predictions, and ...
AI vs Machine Learning vs Deep Learning | Machine Learning Training with Python | Edureka
Machine Learning Training with Python: ) This Edureka Machine Learning tutorial (Machine Learning Tutorial with Python Blog: ..
See complete series on sorting algorithms here: In this ..
17. Learning: Boosting
MIT 6.034 Artificial Intelligence, Fall 2010 View the complete course: Instructor: Patrick Winston Can multiple weak classifiers be ..
Natural Language Processing With Python and NLTK p.1 Tokenizing words and Sentences
Natural Language Processing is the task we give computers to read and understand (process) written text (natural language). By far, the most popular toolkit or ...
Build a Neural Net in 4 Minutes
Only a few days left to signup for my Decentralized Applications course! How does a Neural network work? Its the basis of deep ..
Android vitals: debug app performance and reap rewards (Google I/O '18)
Learn about Android vitals and improved tools in the Play Console and Android Studio to help improve your app quality. This session will explain how app ...