If you believe anything can and will be automated with artificial intelligence (AI), then you might not be surprised to know how many notable media organizations including The New York Times, Associated Press, Reuters, Washington Post, and Yahoo! Sports already use AI to generate content. The Press Association, for example, can now produce 30,000 local news stories a month using AI. You might think that these are formulaic who, what, where and when stories and you are right, some of them certainly are. But, today, AI-written content has expanded beyond formulaic writing to more creative writing endeavors such as poetry and novels. Read More
Daily Archives: March 30, 2019
Incremental learning algorithms and applications
Incremental learning refers to learning from streaming data, which arrive over time, with limited memory resources and, ideally, without sacrificing model accuracy. This setting fits different application scenarios such as learning in changing environments, model personalisation, or lifelong learning, and it offers an elegant scheme for big data processing by means of its sequential treatment. In this contribution, we formalise the concept of incremental learning, we discuss particular challenges which arise in this setting, and we give an overview about popular approaches, its theoretical foundations, and applications which emerged in the last years. Read More
Can we stop AI outsmarting humanity?
It began three and a half billion years ago in a pool of muck, when a molecule made a copy of itself and so became the ultimate ancestor of all earthly life.
It began four million years ago, when brain volumes began climbing rapidly in the hominid line.
Fifty thousand years ago with the rise of Homo sapiens sapiens.
Ten thousand years ago with the invention of civilization.
Five hundred years ago with the invention of the printing press.
Fifty years ago with the invention of the computer.
In less than thirty years, it will end. Read More
Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing
Deep convolutional neural network (DCNN) based supervised learning is a widely practiced approach for large-scale image classification. However, retraining these large networks to accommodate new, previously unseen data demands high computational time and energy requirements. Also, previously seen training samples may not be available at the time of retraining. We propose an efficient training methodology and incrementally growing DCNN to allow new classes to be learned while sharing part of the base network. Our proposed methodology is inspired by transfer learning techniques, although it does not forget previously learned classes. An updated network for learning new set of classes is formed using previously learned convolutional layers (shared from initial part of base network) with addition of few newly added convolutional kernels included in the later layers of the network. We evaluated the proposed scheme on several recognition applications. The classification accuracy achieved by our approach is comparable to the regular incremental learning approach (where networks are updated with new training samples only, without any network sharing), while achieving energy efficiency, reduction in storage requirements, memory access and training time. Read More
Transfer Incremental Learning Using Data Augmentation
Due to catastrophic forgetting, deep learning remains highly inappropriate when facing incremental learning of new classes and examples over time. In this contribution, we introduce Transfer Incremental Learning using Data Augmentation (TILDA). TILDA combines transfer learning from a pre-trained Deep Neural Network (DNN) as feature extractor, a Nearest Class Mean (NCM) inspired classifier and majority vote using data augmentation on both training and test vectors. The obtained methodology allows learning new examples or classes on the fly with very limited computational and memory footprints. We perform experiments on challenging vision datasets and obtain performance significantly better than existing incremental counterparts. Read More
Using Transfer Learning to Introduce Generalization in Models
Researchers often try to capture as much information as they can, either by using existing architectures, creating new ones, going deeper, or employing different training methods. This paper compares different ideas and methods that are used heavily in Machine Learning to determine what works best. These methods are prevalent in various domains of Machine Learning, such as Computer Vision and Natural Language Processing (NLP). Read More
Rick's Cafe AI 