AI deals with the area of developing computing systems which are capable of performing tasks that humans are very good at, for example recognising objects, recognising and making sense of speech, and decision making in a constrained environment. Narrow AI: the field of AI where the machine is designed to perform a single task and the machine gets very good at performing that particular task. However, once the machine is trained, it does not generalise to unseen domains. This is the form of AI that we have today, for example Google Translate. Artificial General Intelligence (AGI): a form of AI that can accomplish any intellectual task that a human being can do.

Diabetic Retinopathy is the leading cause of blindness in the world. At least 90\% of new cases can be reduced with proper treatment and monitoring of the eyes. However, scanning the entire population of patients is a difficult endeavor. Computer-aided diagnosis tools in retinal image analysis can make the process scalable and efficient. In this work, we focus on the problem of localizing the centers of the Optic disc and Fovea, a task crucial to the analysis of retinal scans. Current systems recognize the Optic disc and Fovea individually, without exploiting their relations during learning. We propose a novel approach to localizing the centers of the Optic disc and Fovea by simultaneously processing them and modeling their relative geometry and appearance. We show that our approach improves localization and recognition by incorporating object-object relations efficiently, and achieves highly competitive results.

This manuscript addresses the problem of the automatic lesion boundary detection in dermoscopy, using deep neural networks. An approach is based on the adaptation of the U-net convolutional neural network with skip connections for lesion boundary segmentation task. I hope this paper could serve, to some extent, as an experiment of using deep convolutional networks in biomedical segmentation task and as a guideline of the boundary detection benchmark, inspiring further attempts and researches.

Recently, many researchers have been focusing on the definition of neural networks for graphs. The basic component for many of these approaches remains the graph convolution idea proposed almost a decade ago. In this paper, we extend this basic component, following an intuition derived from the well-known convolutional filters over multi-dimensional tensors. In particular, we derive a simple, efficient and effective way to introduce a hyper-parameter on graph convolutions that influences the filter size, i.e. its receptive field over the considered graph. We show with experimental results on real-world graph datasets that the proposed graph convolutional filter improves the predictive performance of Deep Graph Convolutional Networks.

Sequence generation models such as recurrent networks can be trained with a diverse set of learning algorithms. For example, maximum likelihood learning is simple and efficient, yet suffers from the exposure bias problem. Reinforcement learning like policy gradient addresses the problem but can have prohibitively poor exploration efficiency. A variety of other algorithms such as RAML, SPG, and data noising, have also been developed from different perspectives. This paper establishes a formal connection between these algorithms. We present a generalized entropy regularized policy optimization formulation, and show that the apparently divergent algorithms can all be reformulated as special instances of the framework, with the only difference being the configurations of reward function and a couple of hyperparameters. The unified interpretation offers a systematic view of the varying properties of exploration and learning efficiency. Besides, based on the framework, we present a new algorithm that dynamically interpolates among the existing algorithms for improved learning. Experiments on machine translation and text summarization demonstrate the superiority of the proposed algorithm.

We aim to build complex humanoid agents that integrate perception, motor control, and memory. In this work, we partly factor this problem into low-level motor control from proprioception and high-level coordination of the low-level skills informed by vision. We develop an architecture capable of surprisingly flexible, task-directed motor control of a relatively high-DoF humanoid body by combining pre-training of low-level motor controllers with a high-level, task-focused controller that switches among low-level sub-policies. The resulting system is able to control a physically-simulated humanoid body to solve tasks that require coupling visual perception from an unstabilized egocentric RGB camera during locomotion in the environment. For a supplementary video link, see https://youtu.be/7GISvfbykLE .

A central challenge faced by memory systems is the robust retrieval of a stored pattern in the presence of interference due to other stored patterns and noise. A theoretically well-founded solution to robust retrieval is given by attractor dynamics, which iteratively clean up patterns during recall. However, incorporating attractor dynamics into modern deep learning systems poses difficulties: attractor basins are characterised by vanishing gradients, which are known to make training neural networks difficult. In this work, we avoid the vanishing gradient problem by training a generative distributed memory without simulating the attractor dynamics. Based on the idea of memory writing as inference, as proposed in the Kanerva Machine, we show that a likelihood-based Lyapunov function emerges from maximising the variational lower-bound of a generative memory. Experiments shows it converges to correct patterns upon iterative retrieval and achieves competitive performance as both a memory model and a generative model.

Self-Driving Pi Car A deep neural network based self-driving car, that combines Lego Mindstorms NXT with the computational power of a Raspberry Pi 3. SOP-Generator A simple LSTM based Statement of Purpose Generator for grad school. EuclidesDB A multi-model machine learning feature database that is tight coupled with PyTorch and provides a backend for including and querying data on the model feature space. While other packages and more exact methods exist to model uplift.

Changing the Game At HELIX, we apply the latest developments in AI, computer vision, LIDAR and cloud computing at scale for the benefit of real estate owners, property managers and tenants. Our solutions are in closed beta and only available to a select group of the most admired companies in the world. If you want to play a key role in this transformation, send us a note. The Role As a Senior Research Engineer you will join our growing Applied R&D team in London and will drive technical innovations that fuel our product. You will conduct applied research projects from prototyping to deploying deep learning methods applied to 2D and 3D computer vision.

While you're asking yourself how to leverage your business on machine/deep learning, many questions come up from data collection, preparation, labeling, modeling, training, testing, continuous development, continuous integration... BuQuaTi's Machine Learning Platform (BQT-MLP) is the unique platform in the market which can serve all three Google TensorFlow models; TensorFlow, TensorFlow Mobile, TensorFlow Lite. Our professional services acompanied by our Machine Learning Platform (BQT-MLP) enable your smart digital journey end to end; simplification, preparation, modeling, development, deployment, operations, analytics. More than 60% of the efforts in a data project like Machine Learning, go into data preparation; cleansing, transforming, and labeling. We manage all aspects, and propose efficient, a-class solutions.