Introducing adversarial examples in deep learning vision models
We have seen the advent of state-of-the-art (SOTA) deep learning models for computer vision ever since we started getting bigger and better compute (GPUs and TPUs), more data (ImageNet etc.) and easy to use open-source software and tools (TensorFlow and PyTorch). Every year (and now every few months!) we see the next SOTA deep learning model dethrone the previous model in terms of Top-k accuracy for benchmark datasets. The following figure depicts some of the latest SOTA deep learning vision models (and doesn’t depict some like Google’s BigTransfer!). Read More
Daily Archives: November 5, 2020
Introducing software fuzzing – part of AI and ML in DevOps
The lines between the real world and the digital world have been consistently blurring for years, and with that, software has bloomed. Physicists are hypothesizing that information can be considered a form of matter, the fifth form of matter in fact.
More and more, software is linked to the quality of our lives. That means the quality of our software will fundamentally direct the quality of our experience, so there’s never been a more important time to seek out ways to improve our DevOps. One of the tools that helps us explore that is ML. Read More
The Future of AI is Artificial Sentience
How do you *feel* about that?
Much of today’s discussion around the future of artificial intelligence is focused on the possibility of achieving artificial general intelligence. Essentially, an AI capable of tackling an array of random tasks and working out how to tackle a new task on its own, much like a human, is the ultimate goal. But the discussion around this kind of intelligence seems less about if and more about when at this stage in the game. With the advent of neural networks and deep learning, the sky is the actual limit, at least that will be true once other areas of technology overcome their remaining obstructions. Read More
21 amazing Youtube channels for you to learn AI, Machine Learning, and Data Science for free
This is the perfect moment to start learning something new, and why not start with AI?
I know the pandemic is keeping everyone at home, home working is becoming the new normal for many of us, and it is hard to find good presential training these days, but it does not mean that you need to stop learning!
I would say that this is the perfect moment to start learning something new, and why not start with Data Science? Read More
It’s Hard For Neural Networks to Learn the Game of Life
Efforts to improve the learning abilities of neural networks have focused mostly on the role of optimization methods rather than on weight initializations. Recent findings, however, suggest that neural networks rely on lucky random initial weights of subnetworks called “lottery tickets” that converge quickly to a solution [8].To investigate how weight initializations affect performance, we examine small convolutional networks that are trained to predict nsteps of the two-dimensional cellular automaton Conway’s Game of Life[3], the update rules of which can be implemented efficiently in a2n+ 1layer convolutional network. We find that networks of this architecture trained on this task rarely converge. Rather, networks require substantially more parameters to consistently converge. In addition, near-minimal architectures are sensitive to tiny changes in parameters: changing the sign of a single weight can cause the network to fail to learn. Finally, we observe a critical valued0such that training minimal networks with examples in whichc ells are alive with probabilityd0dramatically increases the chance of convergence to a solution. We conclude that training convolutional neural networks to learn the input/output function represented by nsteps of Game of Life exhibits many characteristics predicted by the lottery ticket hypothesis [8], namely, that the sizeof the networks required to learn this function are often significantly larger than the minimal network required to implement the function. Read More
The AI Company Helping the Pentagon Assess Disinfo Campaigns
In September, Azerbaijan and Armenia renewed fighting over Nagorno-Karabakh, a disputed territory in the Caucasus mountains. By then, an information warfare campaign over the region had been underway for several months.
The campaign was identified using artificial intelligence technology being developed for US Special Operations Command (SOCOM), which oversees US special forces operations.
The AI system, from Primer, a company focused on the intelligence industry, identified key themes in the information campaign by analyzing thousands of public news sources. In practice, Primer’s system can analyze classified information too. Read More
Rick's Cafe AI 