271
Audio Adversarial Examples
Figure from our paper: given any waveform, we can modify it slightly to produce another (similar) waveform that transcribes as any different target phrase.
New
The latest blog posts to take off on Hacker News. 292 posts.
272
Kaggle Learn review: there is a deep learning track and it is worth your time
Right from my undergrad days when I was starting out with machine learning to this date, my admiration for Kaggle continues to grow. In addition to being synonymous with and popularizing data scien…
273
Interactive GPU Programming, Part 1: Hello CUDA
Today, fast number crunching means parallel programs that run on Graphical Processing Units (GPUs). Thanks to the recent highly publicized deep learning and ...
274
275
The UX of AI
Explore Google Design’s human-centered approach to UX design for AI. Learn how Google Clips uses ML for user-friendly, private experiences. Discover more.
276
Using Self-Organizing Maps to Solve the Traveling Salesman Problem
Using Self-Organizing Maps to solve the Traveling Salesman Problem The Traveling Salesman Problem is a well known challenge in Computer Science: it consists on finding the shortest route possible that traverses all cities in a given map only once. Although its simple explanation, this problem is, indeed, NP-Complete…
277
278
279
Faster R-CNN: Down the rabbit hole of modern object detection
In this post, I'll explain the architecture of Faster R-CNN, starting with a high level overview, and then go over the details for each of the components. You'll be introduced to base networks, anchors as well as the region proposal network.
280
281
Cloud AutoML: Making AI accessible to every business
To make AI accessible to every business, we’re introducing Cloud AutoML, which helps businesses with limited ML expertise start building their own high-quality custom mo…
282
283
One model to learn them all
One model to learn them all Kaiser et al., arXiv 2017 You almost certainly have an abstract conception of a banana in your head. Suppose you ask me if I’d like anything to eat. I can say the word ‘…
284
285
286
287
288
289
290
Algorithm efficiency comes from problem information
This is a high level post about algorithms (especially mathematical, scientific, and data analysis algorithms) which I hope can help people who are not researchers or numerical software developers better understand how to choose and evaluate algorithms. When scientists and programmers think about efficiency of…
291
Introducing Preemptible GPUs
In May 2015, Google Cloud introduced Preemptible VM instances to dramatically change how you think about (and pay for) computational resources for high-throughput batch computing, machine learning, scientific and technical workloads. Then last year, we introduced lower pricing for Local SSDs attached to Preemptible…
292
