According to IDG’s 2020 Cloud Computing Study, 92% of organizations have at least some sort of cloud footprint in regard to their IT environment. Therefore, traditional cloud security approaches must evolve to keep up with the dynamic infrastructure and challenges that cloud environments present – most notably, the inundation of data insights generated within the cloud.
More than one-third of IT security managers and security analysts ignore threat alerts when the queue is full. This is a common issue that is driving the high demand for machine learning-based analytics, as it helps security teams sift through massive amounts of data to prioritize risks and vulnerabilities and make more informed decisions
However, a word of caution when using machine learning-based technology: the age-old garbage-in, garbage-out applies to security-focused machine learning engines. If your data is bad, then your machine learning tools will be insufficient, making your security infrastructure vulnerable to attack and putting your organization at risk for a wide-spread security breach. Read More
Monthly Archives: April 2021
NVIDIA and Cloudflare offer AI to all developers
The partnership said its workers developer platform is faster and 75% less expensive than AWS Lambda.
NVIDIA and Cloudflare announced a partnership that will “put AI into the hands of developers everywhere.”
Working with NVIDIA, Cloudflare will offer artificial intelligence (AI) tools to developers on top of its workers developer platform, making it “easier and faster for developers to build the types of applications that will power the future all within a platform.” On the Cloudflare blog, it claimed that it is faster and 75% less expensive than AWS Lambda. Read More
Natural language processing: A cheat sheet (free PDF)
Natural language processing (NLP) is a cross-discipline approach to making computers hear, process, understand, and duplicate human language. Fields including linguistics, computer science, and machine learning are all a part of the process of NLP, the results of which can be seen in things like digital assistants, chatbots, real-time translation apps, and other language-using software.
Make no mistake: NLP is a complicated field that one can spend years studying. This free PDF download from TechRepublic contains the basics about NLP, details how it can benefit businesses, and explains where to get started with its implementation. Read More
Self-Supervised Equivariant Scene Synthesis from Video
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into background, characters, and their animations. Our method capitalizes on moving characters being equivariant with respect to their transformation across frames and the background being constant with respect to that same transformation. After training, we can manipulate image encodings in real time to create unseen combinations of the delineated components. As far as we know, we are the first method to perform unsupervised extraction and synthesis of interpretable background, character, and animation. We demonstrate results on three datasets: Moving MNIST with backgrounds, 2D video game sprites, and Fashion Modeling. Read More
#image-recognitionChina’s GPT-3? BAAI Introduces Superscale Intelligence Model ‘Wu Dao 1.0’
The Beijing Academy of Artificial Intelligence (BAAI) releases Wu Dao 1.0, China’s first large-scale pretraining model.
Since the May 2020 release of OpenAI’s GPT-3, AI researchers have embraced super-large-scale pretraining models. Packing an epoch-making 175 billion parameters, GPT-3 has achieved excellent performance across multiple natural language processing (NLP) tasks. Despite their size and power however, such models still lack common sense or cognitive abilities, and so struggle with complex reasoning tasks like open dialogue, knowledge-based Q&A, visual reasoning, etc.
In a bid to promote the research and development of China’s own large-scale pretraining models and further explore universal intelligence from a more fundamental perspective, the Beijing Academy of Artificial Intelligence (BAAI) recently unveiled Wu Dao 1.0, China’s first homegrown super-scale intelligent model system. Read More
TransGAN: Two Transformers Can Make One Strong GAN
The recent explosive interest on transformers has suggested their potential to become powerful “universal” models for computer vision tasks,such as classification, detection, and segmentation. However, how further transformers can go- are they ready to take some more notoriously difficult vision tasks, e.g., generative adversarial networks (GANs)? Driven by that curiosity, we conduct the first pilot study in building a GAN completely free of convolutions, using only pure transformer-based architectures. Our vanilla GAN architecture, dubbed TransGAN, consists of a memory-friendly transformer-based generator that progressively increases feature resolution while decreasing embedding dimension, and a patch-level discriminator that is also transformer-based. We then demonstrate TransGAN to notably benefit from data augmentations (more than standard GANs), a multi-task co-training strategy for the generator, and a locally initialized self-attention that emphasizes the neighborhood smoothness of natural images. Equipped with those findings, TransGAN can effectively scaleup with bigger models and high-resolution image datasets. Our best architecture achieves highly competitive performance compared to current state-of-the-art GANs based on convolutional backbones. Specifically, TransGAN sets newstate-of-the-art IS score of 10.10 and FID score of 25.32 on STL-10. It also reaches competitive8.63 IS score and 11.89 FID score on CIFAR-10, and 12.23 FID score on CelebA64×64, respectively. We also conclude with a discussion of the current limitations and future potential of TransGAN. Read More
Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks
We identify label errors in the test sets of 10 of the most commonly-used computer vision, natural language, and audio datasets, and subsequently study the potential for these label errors to affect benchmark results. Errors in test sets are numerous and widespread: we estimate an average of 3.4% errors across the 10 datasets,1where for example 2916 label errors comprise 6% of the ImageNet validation set.Putative label errors are identified using confident learning algorithms and then human-validated via crowdsourcing (54% of the algorithmically-flagged candidates are indeed erroneously labeled). Traditionally, machine learning practitioners choose which model to deploy based on test accuracy — our findings advise caution here, proposing that judging models over correctly labeled test sets maybe more useful, especially for noisy real-world datasets. Surprisingly, we find that lower capacity models may be practically more useful than higher capacity models in real-world datasets with high proportions of erroneously labeled data.For example, on ImageNet with corrected labels: ResNet-18 outperforms ResNet-50 if the prevalence of originally mislabeled test examples increases by just 6%. OnCIFAR-10 with corrected labels: VGG-11 outperforms VGG-19 if the prevalence of originally mislabeled test examples increases by just 5%. Read More
China tech groups given a month to fix antitrust practices
Regulators summon 34 online companies after imposing record fine on Alibaba
China’s tech companies have been given a month to fix anti-competitive practices and publicly pledge to follow the rules or risk suffering the same fate as ecommerce group Alibaba, which was fined $2.8bn at the weekend.
China’s market and internet regulators and the tax administration issued the ultimatum at a meeting on Tuesday with the country’s 34 leading tech companies, including Tencent, ByteDance, Meituan and Alibaba. Read More
Europe eyes strict rules for artificial intelligence
Non-compliant companies could face a fine of up to €20 million or 4 percent of turnover.
The European Union wants to avoid the worst of what artificial intelligence can do — think creepy facial recognition tech and many, many Black Mirror episodes — while still trying to boost its potential for the economy in general.
According to a draft of its upcoming rules, obtained by POLITICO, the European Commission would ban certain uses of “high-risk” artificial intelligence systems altogether, and limit others from entering the bloc if they don’t meet its standards. Companies that don’t comply could be fined up to €20 million or 4 percent of their turnover. The Commission will unveil its final regulation on April 21. Read More
Machine Learning Systems Design
… Machine Learning Systems Design is a freely-available course from Stanford taught by Chip Huyen which aims to give you a toolkit for designing, deploying, and managing practical machine learning systems. Here’s what the course website has to say about what machine learning systems design is, in a succinct manner:
Machine learning systems design is the process of defining the software architecture, infrastructure, algorithms, and data for a machine learning system to satisfy specified requirements.
Besides the course material on the website, Chip has written these related machine learning systems design notes available on her website; there may be overlap between this material and that which is on the course website, as I have not done a thorough comparison. Read More
Rick's Cafe AI 