In this paper, we propose a new event memory architecture (MemNet) for recurrent neural networks, which is universal for different types of time series data such as scalar, multivariate or symbolic. Unlike other external neural memory architectures, it stores key-value pairs, which separate the information for addressing and for content to improve the representation, as in the digital archetype. Moreover, the key-value pairs also avoid the compromise between memory depth and resolution that applies to memories constructed by the model state. One of the MemNet key characteristics is that it requires only linear adaptive mapping functions while implementing a nonlinear operation on the input data. MemNet architecture can be applied without modifications to scalar time series, logic operators on strings, and also to natural language processing, providing state-of-the-art results in all application domains such as the chaotic time series, the symbolic operation tasks, and the question-answering tasks (bAbI). Finally, controlled by five linear layers, MemNet requires a much smaller number of training parameters than other external memory networks as well as the transformer network. The space complexity of MemNet equals a single self-attention layer. It greatly improves the efficiency of the attention mechanism and opens the door for IoT applications.

Various work has suggested that the memorability of an image is consistent across people, and thus can be treated as an intrinsic property of an image. Using computer vision models, we can make specific predictions about what people will remember or forget. While older work has used now-outdated deep learning architectures to predict image memorability, innovations in the field have given us new techniques to apply to this problem. Here, we propose and evaluate five alternative deep learning models which exploit developments in the field from the last five years, largely the introduction of residual neural networks, which are intended to allow the model to use semantic information in the memorability estimation process. These new models were tested against the prior state of the art with a combined dataset built to optimize both within-category and across-category predictions. Our findings suggest that the key prior memorability network had overstated its generalizability and was overfit on its training set. Our new models outperform this prior model, leading us to conclude that Residual Networks outperform simpler convolutional neural networks in memorability regression. We make our new state-of-the-art model readily available to the research community, allowing memory researchers to make predictions about memorability on a wider range of images.

Lifelong learning is a very important step toward realizing robust autonomous artificial agents. Neural networks are the main engine of deep learning, which is the current state-of-the-art technique in formulating adaptive artificial intelligent systems. However, neural networks suffer from catastrophic forgetting when stressed with the challenge of continual learning. We investigate how to exploit modular topology in neural networks in order to dynamically balance the information load between different modules by routing inputs based on the information content in each module so that information interference is minimized. Our dynamic information balancing (DIB) technique adapts a reinforcement learning technique to guide the routing of different inputs based on a reward signal derived from a measure of the information load in each module. Our empirical results show that DIB combined with elastic weight consolidation (EWC) regularization outperforms models with similar capacity and EWC regularization across different task formulations and datasets.

From the "Mona Lisa" to the "Girl with a Pearl Earring," some images linger in the mind long after others have faded. Ask an artist why, and you might hear some generally-accepted principles for making memorable art. Now there's an easier way to learn: ask an artificial intelligence model to draw an example. A new study using machine learning to generate images ranging from a memorable cheeseburger to a forgettable cup of coffee shows in close detail what makes a portrait or scene stand out. The images that human subjects in the study remembered best featured bright colors, simple backgrounds, and subjects that were centered prominently in the frame.

Recent studies on automatic neural architectures search have demonstrated significant performance, competitive to or even better than hand-crafted neural architectures. However, most of the existing network architecture tend to use residual, parallel structures and concatenation block between shallow and deep features to construct a large network. This requires large amounts of memory for storing both weights and feature maps. This is challenging for mobile and embedded devices since they may not have enough memory to perform inference with the designed large network model. To close this gap, we propose MemNet, an augment-trim learning-based neural network search framework that optimizes not only performance but also memory requirement. Specifically, it employs memory consumption based ranking score which forces an upper bound on memory consumption for navigating the search process. Experiment results show that, as compared to the state-of-the-art efficient designing methods, MemNet can find an architecture which can achieve competitive accuracy and save an average of 24.17% on the total memory needed.

Earlier this week, Facebook updated its iOS app offering voice descriptions of photographs uploaded by its users. A big step forward for accessibility, but it's far from the only company looking to make the world more inclusive to the visually impaired. In fact, rapid advances in artificial intelligence, machine vision and image-recognition technology are opening up the digital world to the blind and visually impaired – and helping them to interact with their surroundings. One interesting example is Austrian start-up BLITAB, which has created the first ever tactile tablet for blind and visually impaired people, dubbed "the iPad for the blind". As Kristina Tsvetanova, co-founder & CEO at BLITAB Technology, explains, the device looks similar to an ebook but displays small physical bubbles instead of using a screen, which means users can view whole pages of braille text at once, without any mechanical elements.

Earlier this week, Facebook updated its iOS app offering voice descriptions of photographs uploaded by its users. A big step forward for accessibility, but it's far from the only company looking to make the world more inclusive to the visually impaired. In fact, rapid advances in artificial intelligence, machine vision and image-recognition technology are opening up the digital world to the blind and visually impaired – and helping them to interact with their surroundings. One interesting example is Austrian start-up BLITAB, which has created the first ever tactile tablet for blind and visually impaired people, dubbed "the iPad for the blind". As Kristina Tsvetanova, co-founder & CEO at BLITAB Technology, explains, the device looks similar to an ebook but displays small physical bubbles instead of using a screen, which means users can view whole pages of braille text at once, without any mechanical elements.

Rapid advances in artificial intelligence, machine vision and image-recognition technology are opening up the digital world to the blind and visually impaired – and helping them to interact with their surroundings. One interesting example is Austrian start-up BLITAB, which has created the first ever tactile tablet for blind and visually impaired people, dubbed "the iPad for the blind". As Kristina Tsvetanova, co-founder & CEO at BLITAB Technology, explains, the device looks similar to an ebook but displays small physical bubbles instead of using a screen, which means users can view whole pages of braille text at once, without any mechanical elements. "It offers a completely new user experience for braille and non-braille readers via touch navigation, text-to-speech output and Perkins-style keyboard application. It also enables the direct conversion of any text file into braille and obtains information via NFC tags. BLITAB is not just a tablet, it is a platform for all existing and future software applications for blind readers," she says.