Deep Learning — the use of neural networks with modern techniques to tackle problems ranging from computer vision to speech recognition and synthesis — is certainly a current buzzword. However, at the core is a set of powerful methods for organizing self-learning systems. Multi-layer neural networks aren’t new, but there is a resurgence of interest primarily due to the availability of massively parallel computation platforms disguised as video cards.
The problem is getting started in something like this. There are plenty of scholarly papers that can be hard to wade through. Or you can grab some code from GitHub and try to puzzle it out.
A better idea would be to take a free class entitled: Practical Deep Learning for Coders, Part 1. The course is free unless you count your investment in time. They warn you to expect to commit about ten hours a week for seven weeks to complete the course. You can see the first installment in the video, below. Continue reading “Practical Deep Learning”
Space. The final frontier. Unfortunately, the vast majority of us are planet-locked until further notice. If you are dedicated hobbyist astronomer, you probably already have the rough positions of the planets memorized. But what if you want to know them exactly from the comfort of your room and educate yourself at the same time? [Shubham Paul] has gone the extra parsec to build a Real-Time Planet Tracker that calculates their locations using Kepler’s Laws with exacting precision.
An Arduino Mega provides the brains, while 3.5-turn-pan and 180-degree-tilt servos are the brawn. A potentiometer and switch allow for for planet and mode selection, while a GPS module and an optional MPU9250 gyroscope/magnetometer let it know where you are. Finally a laser pointer shows the planet’s location in a closed room. And then there’s code: a lot of code.
The hardware side of things — as [Shubham Paul] clarifies — looks a little unfinished because the focus of the project is the software with the intent to instruct. They have included all the code they wrote for the RTPT, providing a breakdown in each section for those who are looking to build their own.
Continue reading “Real-Time Planet Tracker With Laser-Point Accuracy”
[Gerardo Iglesias Galván] decided he wanted to try his hand at bug-bounty hunting — where companies offer to pay hackers for finding vulnerabilities. Usually, this involves getting a device or accessing a device on the network, attacking it as a black box, and finding a way in. [Gerrado] realized that some vendors now supply virtual images of their appliances for testing, so instead of attacking a device on the network, he put the software in a virtual machine and attempted to gain access to the device. Understanding the steps he took can help you shore up your defenses against criminals, who might be after more than just a manufacturer’s debugging bounty.
Continue reading “Hacking a Device That Lives Inside the Matrix”
When you have a large software development team working on a project, monitoring the build server is an important part of the process. When a message comes in from your build servers, you need to take time away from what you’re doing to make sure the build’s not broken and, if it’s broken because of something you did, you have to stop what you’re doing, start fixing it and let people know that you’re on it.
[ridingintraffic]’s team uses Jenkins to automatically build their project and if there’s a problem, it sends a message to a Slack channel. This means the team needs to be monitoring the Slack channel, which can lead to some delays. [ridingintraffic] wanted immediate knowledge of a build problem, so with some software, IoT hardware, and a rotating hazard warning light, the team now gets a visible message that there’s a build problem.
An Adafruit Huzzah ESP8266 board is used as the controller, connected to some RF controlled power outlets via a 434MHz radio module. To prototype the system, [ridingintraffic] used an Arduino hooked up to one of the RF modules to sniff out the codes for turning the power outlets on and off from their remotes. With the codes in hand, work on the Huzzah board began.
An MQTT broker is used to let the Huzzah know when there’s been a build failure. If there is, the Huzzah turns the light beacon on via the power outlets. A bot running on the Slack channel listens for a message from one of the developers saying that problem is being worked on, and when it gets it, it sends the MQTT broker a message to turn the beacon off.
There’s also some separation between the internal network, the Huzzahs, and the Slack server on the internet, and [ridingintraffic] goes over the methods used to communicate between the layers in a more detailed blog post. Now, the developers in [ridingintraffic]’s office don’t need to be glued to the Slack channel, they will not miss the beacon when it signals to start panicking!
Last time, I talked about a simple kind of neural net called a perceptron that you can cause to learn simple functions. For the purposes of experimenting, I coded a simple example using Excel. That’s handy for changing things on the fly, but not so handy for putting the code in a microcontroller. This time, I’ll show you how the code looks in C++ and also tell you more about what you can do when faced with a more complex problem.
Continue reading “Perceptrons in C++”
Most programming languages today look fairly similar. There’s small differences, of course (Python using spaces, Ruby and Perl have some odd-looking constructs). In the 1960s and 1970s, though, a lot of programming languages were pretty cryptic. Algol, APL, and LISP are great examples of unusual looking programming languages. Even FORTRAN and PL/1 were hard to read. RPG and COBOL were attempts to make programming more accessible, although you could argue that neither of them took over the world. Most programming languages today have more similarity to FORTRAN than either of those two languages.
A new programming language, Eve, claims to be based on years of research in programming from a human perspective instead of from the computer’s. The result is a language that works by pattern matching instead of the usual flow of control. It is also made to live inside of Markdown documents that can serve as documentation. You can see a video about Eve, below.
Neither of these are totally new ideas. SNOBOL, AWK, and Prolog all have some pattern-matching involved. [Donald Knuth] was promoting literate programming back in the 1980s. However, Eve understands modern constructs like web browsers.
Continue reading “All About Eve”
When you want a person to do something, you train them. When you want a computer to do something, you program it. However, there are ways to make computers learn, at least in some situations. One technique that makes this possible is the perceptron learning algorithm. A perceptron is a computer simulation of a nerve, and there are various ways to change the perceptron’s behavior based on either example data or a method to determine how good (or bad) some outcome is.
What’s a Perceptron?
I’m no biologist, but apparently a neuron has a bunch of inputs and if the level of those inputs gets to a certain level, the neuron “fires” which means it stimulates the input of another neuron further down the line. Not all inputs are created equally: in the mathematical model of them, they have different weighting. Input A might be on a hair trigger, while it might take inputs B and C on together to wake up the neuron in question.
Continue reading “Machine Learning: Foundations”