Viewing profile — wackspurt

My latest immersion into Beej's guide was through the GIOS course too! It also opened my eyes to the amount of familiarity/expertise my older co-workers had with systems programmin…

Relevant here: "Why don't I take military funding?" by Prof. Benjamin Kuipers. https://web.eecs.umich.edu/~kuipers/opinions/no-military-fun... From the introduction: """ Mostly it'…

>>> becomes illegal if you say you're doing this to be intentionally subpoena-proof I didn't know that. Hmm...

>>> We apply cutting edge machine learning techniques on petabytes of data and thousands of Spark/YARN nodes. I'm curious. Do you use an open-source Java ML library (dl4j, etc.) or…

(Copy-pasting the message I already posted in this thread. Seems more relevant here) I think that adoption of privacy preserving data aggregation/analysis will become the norm. The…

I remember this paper on ad intelligence I read a few weeks ago: "Exploring ADINT: Using Ad Targeting for Surveillance on a Budget — or — How Alice Can Buy Ads to Track Bob". https…

I think that adoption of privacy preserving data aggregation/analysis will become the norm. The most immediate applications are 1) telemetry data that is used for monitoring (for e…

That's funny. I wonder how human intrigues (and the literature/narratives around it) will be affected by ubiquitous computing and networking.

Anomaly detection is performed at two levels: 1. A log key anomaly detection LSTM model (a type of recurrent neural network) predicts the next log message type (log key). If it is …

What you are describing sounds similar to a "quine". A quine is a non-empty computer program which takes no input and produces a copy of its own source code as its only output. htt…

MacroBase's pipeline is broken up into the following operators: Transform, Classify, Explain. I find the Explanation operator very valuable and haven't seen something like this in …

Based on my limited understanding* of differential privacy, it falls short on exactness (of aggregate values) and robustness (against malicious clients). I've lately been studying …

Can anyone here offer advice for doing anomaly detection in distributed systems? I'm not looking for advice on which models to use, per se. I'm more interested in how to go about t…

>> Other people do not expect this because there are papers about how to incentivize neurons to correspond to interesting features. Could you clarify that statement? Are you saying…

Apparently, DP has some detractors. I was told by my signal processing professor that differential privacy wasn't really a solution for privacy preserving data analysis. He said so…

>>>Sentimental neuron sounds fascinating too. I didn't realize individual neurons could be talked about or understood outside of the concept of the NN. I am thinking in terms of "b…

(Apologies for the slightly incoherent post below) I've been noticing a lot of work that digs into ML model internals (as they've done here to find the sentiment neuron) to underst…

Did you use something like Differential Privacy?

"Each time you make a Voice Call on Telegram, a neural network learns from your and your device‘s feedback (naturally, it doesn’t have access to the contents of the conversation, i…

Yes. That would be a story worth reading about because the octopus has a PhD!