AI and big data are perfect companions, right? It's indisputable that access to huge volumes of data allows AI assistants to deliver better, faster, more-accurate responses. But there are downsides too. For example, is this reliance on huge amounts of data sustainable or ethical? And if you need 1,000,000 examples to create an application, do time and money become too big a barrier for many developments?

GPT-3 is all the rage right now. It’s a generative pre-trained deep learning model to produce human-like text. It is created by OpenAI — a laboratory, specializing in AI research. As a writer, a…

Sophisticated malware, such as Emotet and Sality, and advanced persistent threats (APTs), such as the recent SolarStorm attack, emphasize the necessity for advanced detection methods to identify novel, unknown types of malicious network traffic. Current intrusion prevention systems (IPS) typically work based on signature matching and monitoring network traffic for known patterns in the data packets. Such static methods fall short in detecting unknown types of malware-generated network traffic, which calls for more advanced detection techniques that incorporate inspection of the overall packet structure, rather than specific static patterns. In a blog on data leakage from Android apps, Unit 42 researchers demonstrated that unknown traffic types that leak sensitive user information could be detected using machine learning techniques. Based on command and control (C2) traffic from malware, such as Sality and Emotet, this blog analyzes how deep learning models are further able to identify modified and incomplete C2 traffic packets.

You have a piece of paper with text on it, and you want to build a model that can translate this text to another language. How do you approach this? The first problem is the variable size of the text. There's no linear algebra model that can deal with vectors with varying dimensions. The default way of dealing with such problems is to use the bag-of-words Model ( 1).

Autonomous vehicle' is a buzzword that's been circulating in recent decades. However, the development of such a vehicle has posed a significant challenge for automotive manufacturers. This article describes how deep learning autonomous driving and navigation can help to turn the concept into a long-awaited reality. The low-touch economy in a post-pandemic world is driving the introduction of autonomous technologies that can satisfy our need for contactless interactions. Whether it's self-driving vehicles delivering groceries or medicines or robo-taxis driving us to our desired destinations, there's never been a bigger demand for autonomy.

"Deep Learning with Python" is an excellent book that simplifies the intricacies of Deep Learning using Python. The author of this book is none other than the creator of the famed Deep Learning Python API called Keras. François' book uses Keras as the bridge between the world of Deep Learning and Python to gradually build your understanding of the subject with intuitive explanations and practical examples.

More enterprises are incorporating machine learning (ML) into their operations, products, and services. Similar to other workloads, a hybrid-cloud model strategy is used for ML development and deployment. A common strategy is using the excellent toolset and training data offered by public cloud ML services for generic ML capabilities. These ML activities typically improve an organization's quality of service and increase in productivity. But the real differentiation lies within using the organization's unique data and know-how to create what's called differentiated machine learning.

Error-bounded lossy compression is becoming an indispensable technique for the success of today's scientific projects with vast volumes of data produced during the simulations or instrument data acquisitions. Not only can it significantly reduce data size, but it also can control the compression errors based on user-specified error bounds. Autoencoder (AE) models have been widely used in image compression, but few AE-based compression approaches support error-bounding features, which are highly required by scientific applications. To address this issue, we explore using convolutional autoencoders to improve error-bounded lossy compression for scientific data, with the following three key contributions. (1) We provide an in-depth investigation of the characteristics of various autoencoder models and develop an error-bounded autoencoder-based framework in terms of the SZ model. (2) We optimize the compression quality for main stages in our designed AE-based error-bounded compression framework, fine-tuning the block sizes and latent sizes and also optimizing the compression efficiency of latent vectors. (3) We evaluate our proposed solution using five real-world scientific datasets and comparing them with six other related works. Experiments show that our solution exhibits a very competitive compression quality from among all the compressors in our tests. In absolute terms, it can obtain a much better compression quality (100% ~ 800% improvement in compression ratio with the same data distortion) compared with SZ2.1 and ZFP in cases with a high compression ratio.

Deep Learning (DL), in particular deep neural networks (DNN), by design is purely data-driven and in general does not require physics. This is the strength of DL but also one of its key limitations when applied to science and engineering problems in which underlying physical properties--such as stability, conservation, and positivity--and desired accuracy need to be achieved. DL methods in their original forms are not capable of respecting the underlying mathematical models or achieving desired accuracy even in big-data regimes. On the other hand, many data-driven science and engineering problems, such as inverse problems, typically have limited experimental or observational data, and DL would overfit the data in this case. Leveraging information encoded in the underlying mathematical models, we argue, not only compensates missing information in low data regimes but also provides opportunities to equip DL methods with the underlying physics and hence obtaining higher accuracy. This short communication introduces several model-constrained DL approaches--including both feed-forward DNN and autoencoders--that are capable of learning not only information hidden in the training data but also in the underlying mathematical models to solve inverse problems. We present and provide intuitions for our formulations for general nonlinear problems. For linear inverse problems and linear networks, the first order optimality conditions show that our model-constrained DL approaches can learn information encoded in the underlying mathematical models, and thus can produce consistent or equivalent inverse solutions, while naive purely data-based counterparts cannot.

Transfer learning can speed up training in machine learning and is regularly used in classification tasks. It reuses prior knowledge from other tasks to pre-train networks for new tasks. In reinforcement learning, learning actions for a behavior policy that can be applied to new environments is still a challenge, especially for tasks that involve much planning. Sokoban is a challenging puzzle game. It has been used widely as a benchmark in planning-based reinforcement learning. In this paper, we show how prior knowledge improves learning in Sokoban tasks. We find that reusing feature representations learned previously can accelerate learning new, more complex, instances. In effect, we show how curriculum learning, from simple to complex tasks, works in Sokoban. Furthermore, feature representations learned in simpler instances are more general, and thus lead to positive transfers towards more complex tasks, but not vice versa. We have also studied which part of the knowledge is most important for transfer to succeed, and identify which layers should be used for pre-training.