Seem like my training data for the car - perhaps a hint of #bias. 😂 #GeekyJokes #ML #AIJokes

Neural networks have a very interesting aspect – they can be viewed as a simple mathematical model that defines a function. For a given function $f(x)$ which can take any input value of $x$, there will be some kind a neural network satisfying that function. This hypothesis was proven almost 20 years ago (“ Approximation by Superpositions of a Sigmoidal Function ” and “ Multilayer feedforward networks are universal approximators ”) and forms the basis of much of #AI and #ML use cases possible . ...

I was looking at something else and happen to stumble across something called Netron , which is a model visualizer for #ML and #DeepLearning models. It is certainly much nicer than for anything else I have seen. The main thing that stood out for me, was that it supports ONNX , and a whole bunch of other formats (Keras, CoreML), TensorFlow (including Lite and JS), Caffe, Caffe2, and MXNet. How awesome is that? ...

Analog Islands

Someone recently asked me, what are some of the use cases / examples of machine learning. Whilst, this might seem as an obvious aspect to some of us, it isn’t the case for many businesses and enterprises – despite that they uses elements of #ML (and #AI) in their daily life – as a consumer. Whilst, the discussion gets more interesting based on the specific domain and the possibly use cases (of course understanding that some might not be sure f the use case – hence the question in the first place). But, this did get me thinking and wanted to share one of the images we use internally as part of our training that outcomes some of the use cases. ...

Trained a model to create a synthetic sound that sounds like me. This is after training it with about 30 sentences - which isn’t a lot. To create a synthetic voice, you enter some text, using which is then “transcribed” using #AI and your synthetic voice is generated. In my case, at first, I had said AI, which was generated also as “aeey” (you can listen here ). So for the next one, changed the AI to Artificial Intelligence. ...

Over the last few weeks, I built a self-driving car - which essentially is a remote control Rx car that uses a raspberry pi running Python, TensorFlow implementing a end-to-end convolution neural network (CNN) Of course other than being a bit geeky, I do think this is very cool to help understand and get into some of the basic constructs and mechanics around a number of things - web page design, hardware (maker things), and Artificial Intelligence principles. ...

Despite all the cloud talk and where I live, it is like the cloud mecca, for enterprises it is still quite new and many are just starting to think about it. A hard lesson that many of us learn (and partly how we amass our scars) is to design for failures. For those, who run things in their enterprises data center, are quite spoilt I think. Failures are rare, and if machines or state goes down, moving to another one isn’t really a big deal (of course it is a little more complex, and not to say, there isn’t any down time, or business loss, etc.). ...

Recently, a few of us went through a workshop where one of the ‘homework’ was to score oneself, on the following 7 aspects – some of these are attributes that allows one to grow from being (hopefully) good managers to great leaders. In most enterprises, as one grows in their career, managers need to acquire new capabilities – and quickly. What they have, in terms of skills and capabilities and got her or him to this place, won’t be enough for the next step – as the scope and complexity increases it can leave executives underwhelmed. At the core, new executives need support on these seven dimensions that will help them make this transition. ...

Just as last year , I wrote a PowerShell script using which you can download the PowerPoint decks, and, videos from Microsoft Build’s conference, instead of streaming it (or manually download it one by one). You can choose if you want the decks, or the videos, or both. For the videos you can choose the desired resolution (Low, Medium, High) – of course the higher the resolution, the more space is needed. The script also downloads the description and if there is a session image (if there is one). ...

If you were trying to pull the latest source code on your Raspberry Pi for donkeycar, and get the following error, then probably your clock is off (and I guess some nonce is failing). This can happen if your pi had been powered off for a while (as in my case), and it’s clock is off ( clock drift is a real thing) :). ...

Can #AI make me look (more) presentable? The jury is out I think. This is called style transfer, where the style/technique from a kind of painting (could be a photos too) is applied to an image, to create a new image. I took this using the built-in camera on my machine sitting at my desk and then applying the different kind of ‘styles’ on it. Each of these styles are is a separate #deeplearning model that has learned how to apply the relevant style to a source image. ...

Yesterday it worked Today it is not working #AI is like that #Haiku #GeekyHaiku #GeekyJokes

Rather than a beep Or a rude error message, These words: “File not found.” #Haiku #GeekyHaiku #GeekyJokes

One of the challenges we have with AI is that there isn’t any universal definition - it is a broad category that means everything to everyone. Debating the rights, and, the wrongs, and the should’s and the shouldn’t s is another post though. DARPA outlines this as the “programmed ability to process information” and across a certain set of criteria that span across perceiving, learning, abstracting, and, reasoning. ...

Cognitive Bias

When seeing this #CosmosDB is the first thing that comes to mind :)

What is it? What’s the next big thing in computing? Not the #AI or #blockchain’s of the world, that is starting to happen today (albeit a little early)? Quantum computing is one of those next big things, that is on the horizon (probably in the ~5 years range). Why do I care? Why do I care about quantum? Well, some problems are simply not solvable on convention digital computers – the kind we have today – these are called “classical” machines. Even if Moore’s law did continue (and that is a whole different debate), are the still some problems whose scaling obey a different set of properties and law; and the double of transistors on a chip wont really help. In fact, some of these problems require longer than the lifetime of the universe – and that is with the biggest, and fastest supercomputers available! ...

At a recent internal meeting, we were discussing productivity and the various levels of distractions that one has these days. Did you know that there is a hierarchy of digital distractions (see image below). No wonder, in todays connected, and agile world, for some people why it is so difficult to get any actual work done (that is not to suggest that they are not busy of course). At this meeting, analogy of the distraction was coined as the “monkey” – the monkey that each of us has on our shoulder and the constant attention it demands – I.e. the distraction. And we all know we cannot control this monkey and bottle it up. The idea isn’t to try and bottle it up, which will rattle it more trying to get out and demand more attention – but rather let it out in a controlled manner for some time – similar to how one would take a dog out for a walk (of course different outcomes) ! 😄 ...

Parenting geek

I wakey wakey. Production release today. No breaky breaky. #Haiku #GeekyHaiku #GeekyJokes

Chaos reigns within. Reflect, repent, and reboot. Order shall return. #haiku #GeekyHaiku

Ridiculous mess iOS development conceived by hipsters #Haiku #GeekyHaiku #GeekyJokes

Thinking about #machinelearning? It will be helpful to understand some numerical computations and concepts that affect the #ML algorithm. One might not interact with these directly, but we surely can feel the effect. The things you need to think about are: 1. Overflow and underflow - thinking of them as rounding up or down errors that shift the functions enough, and compounded across the iterations cam be devastating. Of course can also easily get to division by zero. ...