End-to-end machine learning project processes [closed] - machine-learning

Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question does not appear to be about programming within the scope defined in the help center.
Closed 1 year ago.
Improve this question
I've read a book chapter that walks you through all the steps involved in an end-to-end machine learning project. After doing all the practical exercises I'm still not quite sure that my way of thinking about the whole process is right.
I've tried to depict it in the following flowchart:
Is this the right way of thinking about all the steps in an ML project? Is something missing?

Seems decent.
Just want to mention that the cross-validation and model-selection in your short-listing step could also include tuning the pipelines, because different types of transformations may be suitable to different models.
For example, when there are sparse or categorical features, the pipelines may matter a lot.

Related

In transfer learning what is the custom part of the network called? [closed]

Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question does not appear to be about programming within the scope defined in the help center.
Closed 2 years ago.
Improve this question
I was wondering if the part of the network with frozen weights has a specific name. Similarly, I'd want to know whether the custom-made part also has a specific name.
I don't think there is any scientific terminology for the part of the model, however, researchers do use the terminology for the tasks and domains for the pre-trained and custom models being used for transfer learning - Source and Target tasks / domains.
More information to this definition can be found in the IEEE paper A Survey on Transfer Learning (Sinno Jialin Pan and Qiang Yang)
Side Note: In my personal experience though, in industry, we usually call the Source task's model as the Source model / pre-trained model, and the Target task's model as the downstream estimator / downstream model.

Why are there no dropout layers in inception net? [closed]

Closed. This question does not meet Stack Overflow guidelines. It is not currently accepting answers.
This question does not appear to be about programming within the scope defined in the help center.
Closed 2 years ago.
Improve this question
I recently was implementing the InceptionNet and came across the scenario where the dropout layer was not implemented in the network at all in the early or mid stages. Any particular reason for this?
You can see this paper posted model:
It actually has a slight regularization effect which is similar to dropout.
Think like that we are choosing every node with a certain possibility for that
layer so we creating our NN architecture with a possibilities. Similar
situation is valid also in here but this time we apply the all possibilities.
Hence, inception network helps to prevent over fitting the parameters so that
learning is happening for more deeper understanding please check out the
original paper but that is just an observation not a prove.

Which technique is used in Auto Answering user queries in Artificial Intelligence? [closed]

Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 5 years ago.
Improve this question
I have a paragraph, system has to understand it and it should answer all the questions asked by the user. Please name the techniques and methodologies.
It all depends on the problem that you are trying to solve, the data available to you and the underlying domain. Lets get to it one by one:
Type of Problem
There are multiple types of question answering systems, like one word answers based on extract the exact answer from various sentences, or returning the most similar sentence from a list of sentences based on the question asked by the user, using various similarity and embedding techniques. I think this paper : Teaching Machines to Read and Comprehend should be a good place to start getting an idea about such systems.
Dataset
Next comes the dataset for such systems. Now there are various datasets available for question answering systems like :
SQuAD dataset
QA dataset based on Wikipedia Articles
Facebook bAbI dataset
AllenAI dataset based elementary Science question
NewsQA datset
Methodologies
Well there are multiple ways to go about solving this problem. It would be difficult to list all of them in one answer, but I can provide you some references:
Deep Learning for Question Answering
Various Deep Learning models on Question answering
SquAD dataset Leaderboard
Question Answering based on Word Alignment
Attention Based Question Answering
Reasoning-based QA

How to write a program that outputs source code [closed]

Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 6 years ago.
Improve this question
This might not be the right place for this to ask, but I am interested in artificial neural networks and want to learn more.
How do you design a network and train it on source code so it can come up with programs for, for example, easy number theory problems?
What's the general name of this research field?
This is a hugely interesting, and very hard, problem area. It will probably take you months to read enough to even understand how to attack the problem. Here's a few things that might help you get started, and they are more to show the problems you will face than to provide solutions:
http://karpathy.github.io/2015/05/21/rnn-effectiveness/
Then read this, and related papers:
https://arxiv.org/pdf/1410.5401v2.pdf
Next, you probably want to read the classic papers in program synthesis and generation at the parse tree/AST level (mostly out of MIT, I think, in the early 90s.)
Best of luck. This is not trivial.

Learning approach in machine learning [closed]

Closed. This question needs to be more focused. It is not currently accepting answers.
Want to improve this question? Update the question so it focuses on one problem only by editing this post.
Closed 8 years ago.
Improve this question
(homework problem)
Which of the following problems are best suited for the learning approach?
Classifying numbers into primes and non-primes.
Detecting potential fraud in credit card charges.
Determining the time it would take a falling object to hit the ground.
Determining the optimal cycle for trafic lights in a busy intersection
I'm trying to answer your question without doing your homework.
Basically you can think of machine learning as a way to extract patterns from data where all other approaches fail.
So first clue here: If there is an analytic way to solve the problem then don't use machine learning! The analytic algorithm will likely be faster, more efficient, and 100% correct.
Second clue is: There has to be a pattern in the data. If you as a human see a pattern, machine learning can find it too. If lots of smart humans who are experts of the respective domain don't see a pattern then machine learning will most likely fail. Chaos can not be learned, i.e. classified/predicted.
That should answer your question. Make sure to also read the summary on wikipedia to get an idea whether a problem can be solved using supervised, unsupervised, or reinforcement learning.

Resources