Keras: Embrace Randomness
Sumber: https://machinelearningmastery.com/randomness-in-machine-learning/
Applied Machine Learning adalah pintu gerbang untuk terobosan dan perubahan pola pikir.
Memahami peran keacakan dalam algoritma machine learning adalah salah satu terobosan tersebut.
Setelah anda mendapatkannya, anda akan melihat berbagai hal secara berbeda. Dalam cahaya sinar yang sama sekali baru. Hal-hal seperti memilih antara satu algoritma dan lainnya, penyetelan hyperparameter dan hasil pelaporan.
Anda juga akan mulai melihat abuse di mana-mana. Klaim kinerja tanpa didukung yang memadai.
Dalam tulisan ini, mata anda akan dibuka secara perlahan tentang peran angka random dalam machine learning. Jika akan diberikan tool untuk merangkul randomness (ketidakpastian) tersebut. Agar anda dapat lebih mudah melakukan terobosan.
Mengapa hasil yang diperoleh berbada pada menggunakan data yang sama?
Banyak orang menanyakan pertanyaan ini atau varian dari pertanyaan ini.
Anda tidak sendiri!
Berikut adalah beberapa pertanyaan serupa yang diposting di situs Q&A:
- Why do I get different results each time I run my algorithm?
- Cross-Validation gives different result on the same data
- Why are the weights different in each running after convergence?
- Does the same neural network with the same learning data and same test data in two computers give different results?
Algoritma Machine Learning Menggunakan Angka Random
Algoritma machine learning menggunakan keacakan (randomness).
- Randomness saat Data Collection - Di training dengan data yang berbeda, algoritma machine learning akan membangun model yang berbeda. Itu tergantung pada algoritma. Betapa berbedanya suatu model dengan data yang berbeda disebut varian model (seperti dalam bias-variance trade off). Jadi, data itu sendiri adalah sumber keacakan. Keacakan dalam pengumpulan data.
- Randomness saat Observation Order - Urutan pengamatan yang diberikan pada model mempengaruhi keputusan internal. Beberapa algoritma sangat rentan terhadap hal ini, seperti neural network. Merupakan praktik yang baik untuk mengacak data training secara acak sebelum setiap iterasi training. Bahkan jika algoritme anda tidak rentan. Ini praktik terbaik.
- Randomness dalam Algoritma -
Algorithms harness randomness.
An algorithm may be initialized to a random state. Such as the initial weights in an artificial neural network.
Votes that end in a draw (and other internal decisions) during training in a deterministic method may rely on randomness to resolve.
- Randomness dalam Sampling -
We may have too much data to reasonably work with.
In which case, we may work with a random subsample to train the model.
- Randomness dalam Resampling -
We sample when we evaluate an algorithm.
We use techniques like splitting the data into a random training and test set or use k-fold cross validation that makes k random splits of the data.
The result is an estimate of the performance of the model (and process used to create it) on unseen data. No Doubt
There’s no doubt, randomness plays a big part in applied machine learning.
Random Seeds and Reproducible Results
Run an algorithm on a dataset and get a model.
Can you get the same model again given the same data?
You should be able to. It should be a requirement that is high on the list for your modeling project.
We achieve reproducibility in applied machine learning by using the exact same code, data and sequence of random numbers.
Random numbers are generated in software using a pretend random number generator. It’s a simple math function that generates a sequence of numbers that are random enough for most applications.
This math function is deterministic. If it uses the same starting point called a seed number, it will give the same sequence of random numbers.
Problem solved. Mostly.
We can get reproducible results by fixing the random number generator’s seed before each model we construct.
In fact, this is a best practice.
We should be doing this if not already.
In fact, we should be giving the same sequence of random numbers to each algorithm we compare and each technique we try.
It should be a default part of each experiment we run.
Machine Learning Algorithms are Stochastic
If a machine learning algorithm gives a different model with a different sequence of random numbers, then which model do we pick?
Ouch. There’s the rub.
I get asked this question from time to time and I love it.
It’s a sign that someone really gets to the meat of all this applied machine learning stuff – or is about to.
Different runs of an algorithm with… Different random numbers give… Different models with… Different performance characteristics…
But the differences are within a range.
A fancy name for this difference or random behavior within a range is stochastic.
Machine learning algorithms are stochastic in practice.
Expect them to be stochastic. Expect there to be a range of models to choose from and not a single model. Expect the performance to be a range and not a single value.
These are very real expectations that you MUST address in practice.
Tactics To Address The Uncertainty of Stochastic Algorithms
Thankfully, academics have been struggling with this challenge for a long time.
There are 2 simple strategies that you can use:
Reduce the Uncertainty. Report the Uncertainty.
Tactics to Reduce the Uncertainty
If we get different models essentially every time we run an algorithm, what can we do?
How about we try running the algorithm many times and gather a population of performance measures.
We already do this if we use k-fold cross validation. We build k different models.
We can increase k and build even more models, as long as the data within each fold remains representative of the problem.
We can also repeat our evaluation process n times to get even more numbers in our population of performance measures.
This tactic is called random repeats or random restarts.
It is more prevalent with stochastic optimization and neural networks, but is just as relevant generally. Try it.
Tactics to Report the Uncertainty
Never report the performance of your machine learning algorithm with a single number.
If you do, you’ve most likely made an error.
You have gathered a population of performance measures. Use statistics on this population.
This tactic is called report summary statistics.
The distribution of results is most likely a Gaussian, so a great start would be to report the mean and standard deviation of performance. Include the highest and lowest performance observed.
In fact, this is a best practice.
You can then compare populations of result measures when you’re performing model selection. Such as:
Choosing between algorithms. Choosing between configurations for one algorithm.
You can see that this has important implications on the processes you follow. Such as: to select which algorithm to use on your problem and for tuning and choosing algorithm hyperparameters.
Lean on statistical significance tests. Statistical tests can determine if the difference between one population of result measures is significantly different from a second population of results.
Report the significance as well.
This too is a best practice, that sadly does not have enough adoption. Wait, What About Final Model Selection
The final model is the one prepared on the entire training dataset, once we have chosen an algorithm and configuration.
It’s the model we intend to use to make predictions or deploy into operations.
We also get a different final model with different sequences of random numbers.
I’ve had some students ask:
Should I create many final models and select the one with the best accuracy on a hold out validation dataset.
“No” I replied.
This would be a fragile process, highly dependent on the quality of the held out validation dataset. You are selecting random numbers that optimize for a small sample of data.
Sounds like a recipe for overfitting.
In general, I would rely on the confidence gained from the above tactics on reducing and reporting uncertainty. Often I just take the first model, it’s just as good as any other.
Sometimes your application domain makes you care more.
In this situation, I would tell you to build an ensemble of models, each trained with a different random number seed.
Use a simple voting ensemble. Each model makes a prediction and the mean of all predictions is reported as the final prediction.
Make the ensemble as big as you need to. I think 10, 30 or 100 are nice round numbers.
Maybe keep adding new models until the predictions become stable. For example, continue until the variance of the predictions tightens up on some holdout set. Summary
In this post, you discovered why random numbers are integral to applied machine learning. You can’t really escape them.
You learned about tactics that you can use to ensure that your results are reproducible.
You learned about techniques that you can use to embrace the stochastic nature of machine learning algorithms when selecting models and reporting results.
For more information on the importance of reproducible results in machine learning and techniques that you can use, see the post:
Reproducible Machine Learning Results By Default
Do you have any questions about random numbers in machine learning or about this post?
Ask your question in the comments and I will do my best to answer.