I still see many testers talking about the number of bugs found as some sort of barometer of success in terms of effective testing. But lately I’ve seen this framed around the “quality” of bugs found, rather than just their quantity. Still, you have to be a bit careful here. Let’s talk about this.
You’ll often see questions about the practice of software testing that essentially boil down to this: “Which is better: manual testing or automated testing?” This is how many engineering managers do view the world and while they may throw in more words, what they are asking is that question. And the answer they generally come down to is: “Automated testing is better.” How do testers combat that? And should they?
I previously talked about some heuristics for hiring test specialists. There was an assumption in that post that you do, in fact, want to hire specialist testers. But, of course, that is just an assumption. Perhaps you don’t. And before you say “But of course we do!”, let’s talk about this a little bit.
I’ve talked quite a bit about the interview process for testers. Here I’ll try to distill some of that material around my experiences with hiring test specialists. By this term, I mean exactly what it sounds like: people who have chosen to specialize in the discipline of testing.
In the last post, we defined our neural network by providing it some specific hidden layers that will provide the basis for how the neural network model actually works. We were also able to dig in a bit to what’s happening behind the scenes. In this post, we’ll actually execute the neural network by feeding it the data and evaluating what gets produced as output.
In the previous post in this series we implemented a neural network from top to bottom, essentially allowing you to see how everything works from the start of inputting data to getting results. In this post, we’ll start to create a very similar neural network but I’ll take a bit more time to explain some of the specifics. Fair warning: this is probably going to be the longest post in this series so far because there’s a lot to dig into.
In the previous posts in this series, we got a lot of terminology placed in context, we investigated our data set, we took a dive into some math, and we talked about the life cycle of a neural network. In this post, you’re going to get a rapid-fire tour of creating a neural network from start to finish. The goal won’t be to understand every aspect, but rather just to get functionality working that I can expand on for you.
In the previous post in this series we were able to dive in a bit and get coding. That was a nice balance with the first post which put more emphasis on theory. In this post we’ll deal with some of what’s going on between the coding and the theory. This is where some of the practice comes in.
Here we’ll pick up from the first post and get to work with our machine learning, specifically focusing on getting a data set, exploring it a bit, and then doing some processing on the data to get it into a format that would be usable for a neural network algorithm.
This series will be part of my ongoing topic around machine learning. In these posts my goal is to allow you to deep dive into a common example for those first starting out in the subject. By the end of these posts you will have written and tested a neural network to solve a classification and prediction problem and come away with some understanding of a fast-growing trend in the industry.
I believe that semantics matter. I do realize not all semantics matter equally. But, still: semantics matter. It’s disappointing when otherwise intelligent people seem to dismiss something simply because they feel it’s just semantics. Let’s talk about this.
If you are going to have an AI that “does testing” — as opposed to some other activity like analysis or pattern recognition — you are going to have to move from a focus solely on perception and add the dimension of actions. I’m finding a lot of folks promising “AI-based testing tools” or those eagerly hoping for them are very much confusing this distinction. So let’s talk about it and, as we do, let’s create an illustrative example.
In this post I want to explore how a theory of constraints can be combined with cost of mistake curves to consider how testing operates, first and foremost, around the concept of design. Keeping design cheap at all times is a value of testing that I rarely see articulated. So here I’ll give that articulation a shot.
I get asked this a lot. I’ve been doing some form of testing since the early 1990s and while my initial opportunities were provided by chance, my career was one of choice. Rather than say why I stay in testing, I’ll frame this around some questions and answers that may give some insight of how testing has allowed me to answer certain questions in a career-relevant way.