Collaborating Authors

Deep Learning

A new way to train AI systems could keep them safer from hackers

MIT Technology Review

The context: One of the greatest unsolved flaws of deep learning is its vulnerability to so-called adversarial attacks. When added to the input of an AI system, these perturbations, seemingly random or undetectable to the human eye, can make things go completely awry. Stickers strategically placed on a stop sign, for example, can trick a self-driving car into seeing a speed limit sign for 45 miles per hour, while stickers on a road can confuse a Tesla into veering into the wrong lane. Safety critical: Most adversarial research focuses on image recognition systems, but deep-learning-based image reconstruction systems are vulnerable too. This is particularly troubling in health care, where the latter are often used to reconstruct medical images like CT or MRI scans from x-ray data.

Athlete Pose Detection using openCV and Deep Learning


We all love sport and in our life one time we all wish to get the professional training from the coaches. For everyone it is not possible to afford such fees of the coaches. So we have come with the idea as follows. In every sport the main focus is on angles of the athlete what should be the angle between the hands and legs while doing particular activity. So how it will be if we can detect the angles from the video or photo while doing the particular activity and that angles we can send to the coaches and they can guide the athlete about their mistake and it will help them to improve.

AI Weekly -- AI News & Leading Newsletter on Deep Learning & Artificial Intelligence - Issue #169: China and AI: What the World Can Learn and What It Should Be Wary of


China announced in 2017 its ambition to become the world leader in artificial intelligence (AI) by 2030. While the US still leads in absolute terms, China appears to be making more rapid progress than either the US or the EU, and central and local government spending on AI in China is estimated to be in the tens of billions of dollars.

The Guide to Building Deep Learning Neural Networks


The quantum of data generated, stalls the performance of traditional machine learning methods on a standstill, this paves way for complex neural networks to decode this data with their massive computation power allowing deep learning and reinforcement learning models to train these large neural networks. This makes deep learning an exciting field of study. How do you build deep leading neural networks? Start by importing and load the data. This data may sit on data warehouses, or data lakes or the modern data pipelines.

Artificial intelligence open-source frameworks to learn


The spectrum of artificial intelligence is much broader and includes machine learning, artificial neural networks, deep learning, and machine memory. Add the inclusion of AI in education and the workforce of the future will be better prepared to face the unknown challenges of the workplace of tomorrow. Artificial Intelligence is one of the emerging technologies which tries to simulate human reasoning in AI systems. These times demand future-proofing yourself with the AI technology that is on the edge of becoming the next big evolution. When John McCarthy invented the term Artificial Intelligence in the year 1950 he wouldn't have predicted the wide future of this technology and how far it would travel.

Online Courses


The Deep Learning Training at IT Guru will provide you the best knowledge on deep learning fundamentals, neural networks, natural language processing, etc with live experts. Learning Online Deep learning makes you a master in this subject that includes building blocks, implementing neural networks, programming languages & tools, etc. Our best Deep learning Course module will provide you a way to become certified in Deep learning. So, join hands with ITGuru for accepting new challenges and make the best solutions through Advanced Deep learning. The Online Deep learning Training basics and other features will make you an expert in the Deep learning algorithms, etc to deal with real-time tasks.

Hyperparameter Search with Iterative Sweeps


I've spent several years reproducing and optimizing various deep learning models, primarily for computer vision and NLP, often with extremely short deadlines. My distilled high-level strategy for hyperparameter search is bounded exploration (try a wider range of values for fewer variables) and faster iteration (more short phases of exploration building on each other). I hope this overview of hyperparameter search helps you tune deep learning models a bit faster regardless of the framework or tools you use. Hyperparameter search -- or tuning, or optimization -- is the task of finding the best hyperparameters for a learning algorithm. Such tuning could be done entirely by hand: run a controlled experiment (keep all hyperparameters constant except one), analyze the effect of the single value change, decide based on that which hyperparameter to change next, run the next experiment, and repeat.

10 Interesting Papers To Look Forward To At ICML 2020


Now in its 37th year, ICML (The International Conference on Machine Learning) is known for bringing cutting-edge research on all aspects of machine learning to the fore. This year, 1088 papers have been accepted from 4990 submissions. Here are a few interesting works to look at ICML 2020, which will be held between 13th and 18th of July. Meta-learning relies on deep networks, which makes batch normalization an essential component of meta-learning pipelines. However, there are several challenges that can render conventional batch normalization ineffective, giving rise to the need to rethink normalization in this setting.

Applied Sciences


Biometrics such as fingerprint, iris, face, hand print, hand vein, speech and gait recognition etc. as a means of identity management has become commonplace nowadays for various applications. Biometric systems follow a typical pipeline that is composed of separate preprocessing, feature extraction and classification. Deep learning as a data-driven representation learning approach has been shown to be a promising alternative to conventional data-agnostic and handcrafted pre-processing and feature extraction for biometric systems. Furthermore, deep learning offers an end-to-end learning paradigm to unify preprocessing, feature extraction and recognition based solely on biometric data. The objective of this Special Issue is to invite high-quality, state-of-the-art research papers that deal with challenging issues in advanced deep learning-based biometric systems.