An important aspect of health monitoring is effective logging of food consumption. This can help management of diet-related diseases like obesity, diabetes, and even cardiovascular diseases. Moreover, food logging can help fitness enthusiasts, and people who wanting to achieve a target weight. However, food-logging is cumbersome, and requires not only taking additional effort to note down the food item consumed regularly, but also sufficient knowledge of the food item consumed (which is difficult due to the availability of a wide variety of cuisines). With increasing reliance on smart devices, we exploit the convenience offered through the use of smart phones and propose a smart-food logging system: FoodAI, which offers state-of-the-art deep-learning based image recognition capabilities.

Feature selection seeks a curated subset of available features such that they contain sufficient discriminative information for a given learning task. Online streaming feature selection (OSFS) further extends this to the streaming scenario where the model gets only a single pass at features, one at a time. While this problem setting allows for training high performance models with low computational and storage requirements, this setting also makes the assumption that there is a fixed number of samples, which is often invalidated in many real-world problems. In this paper, we consider a new setting called Online Streaming Feature Selection with Streaming Samples (OSFS-SS) with a fixed class label space, where both the features and the samples are simultaneously streamed. We extend the state-of-the-art OSFS method to work in this setting. Furthermore, we introduce a novel algorithm, that has applications in both the OSFS and OSFS-SS settings, called Geometric Online Adaptation (GOA) which uses a graph-based class conditional geometric dependency (CGD) criterion to measure feature relevance and maintain a minimal feature subset with relatively high classification performance. We evaluate the proposed GOA algorithm on both simulation and real world datasets highlighting how in both the OSFS and OSFS-SS settings it achieves higher performance while maintaining smaller feature subsets than relevant baselines.

Artificial Intelligence (AI) is simulated human intelligence accomplished by computers, robots, or other machines. Sects of AI include language processing, visual recognition, decision-making, speech recognition, conversation, translation, pattern matching and categorization, machine learning, and task accomplishment. Though there are concerns about AI, it is probably the hottest trend in computer science at the moment, with most of the major technology companies, and thousands of startups, offering platforms for AI development. Developers looking to add intelligence to applications can check out the ProgrammableWeb Artificial Intelligence category for the best choices of Application Programming Interfaces (APIs) to tap into and create smarter apps. In this article, we highlight fourteen of the most popular AI APIs according to page visits on ProgrammableWeb.

In this paper a novel framework to tackle speaker recognition using a two-stage attention model is proposed. In recent years, the use of deep neural networks, such as time delay neural network (TDNN), and attention model have boosted speaker recognition performance. However, it is still a challenging task to tackle speaker recognition in severe acoustic environments. To build a robust speaker recognition system against noise, we employ a two-stage attention model and combine it with a TDNN model. In this framework, the attention mechanism is used in two aspects: embedding space and temporal space. The embedding attention model built in embedding space is to highlight the importance of each embedding element by weighting them using self attention. The frame attention model built in temporal space aims to find which frames are significant for speaker recognition. To evaluate the effectiveness and robustness of our approach, we use the TIMIT dataset and test our approach in the condition of five kinds of noise and different signal-noise-ratios (SNRs). In comparison with three strong baselines, CNN, TDNN and TDNN+attention, the experimental results show that the use of our approach outperforms them in different conditions. The correct recognition rate obtained using our approach can still reach 49.1%, better than any baselines, even if the noise is Gaussian white Noise and the SNR is 0dB.

Offline Handwritten Text Recognition (HTR) systems transcribe text contained in scanned images into digital text, an example is shown in Figure 1. We will build a Neural Network (NN) which is trained on word-images from the IAM dataset. As the input layer (and therefore also all the other layers) can be kept small for word-images, NN-training is feasible on the CPU (of course, a GPU would be better). This implementation is the bare minimum that is needed for HTR using TF. We use a NN for our task.

Machine Learning and Artificial Intelligence have performed a great role in the recent years with Google, Microsoft Azure,Amazon and many more in their business and other platforms. But still many of us don't know that we have been experiencing machine learning without knowing it.We have adapted many service and systems and we are unaware of that they are part of our daily life or their origin is machine learning.The most primary use cases are'Spam' detection by email providers and Image tagging by Facebook . Now Facebook automatically tags uploaded images using face (image) recognition technique and Gmail recognizes the pattern or selected words to filter spam messages. Let's take a look at some of the important business problems solved by machine learning. But Machines learning (ML) algorithms and predictive modelling algorithms can significantly help to reduce or eradicate these problems or situation.

The majority of ML research concerns slow, statistical learning of i.i.d. samples from large, labelled datasets. Animals do not learn this way. An enviable characteristic of animal learning is 'episodic' learning - the ability to rapidly memorize a specific experience as a composition of existing concepts, without provided labels. The new knowledge can then be used to distinguish between similar experiences, to generalize between classes, and to selectively consolidate to long-term memory. The Hippocampus is known to be vital to these abilities. AHA is a biologically-plausible computational model of the Hippocampus. Unlike most machine learning models, AHA is trained without any external labels and uses only local and immediate credit assignment. We demonstrate AHA in a superset of the Omniglot classification benchmark. The extended benchmark covers a wider range of known Hippocampal functions by testing pattern separation, completion, and reconstruction of original input. These functions are all performed within a single configuration of the computational model. Despite these constraints, results are comparable to state-of-the-art deep convolutional ANNs. In addition to the demonstrated high degree of functional overlap with the Hippocampal region, AHA is remarkably aligned to current macro-scale biological models and uses biologically plausible micro-scale learning rules.

Google recently released research about a tool called Similar Medical Images Like Yours (SMILY) that uses concept vectors to enhance searching for medical images. The research uses embeddings for image-based search and allows users to influence the search through the interactive refinement of concepts. Google released two papers in succession. The first paper, "Similar image search for histopathology: SMILY" focused on the deep neural network architecture that was used to create the embeddings necessary to find similar images. The second paper, "Human-Centered Tools for Coping with Imperfect Algorithms During Medical Decision-Making," focused on human interaction aspects necessary to improve the usage of the tool created in the first paper.

Singer talked about how AI now has four big "superpowers." Pattern recognition is the most common, and this is used in many domains, including image recognition, speech recognition, and fraud detection. It can be a universal approximator, as it learns the correlation between input and output, and is able to make predictions about results, which allows it to be used for simulations for things like particle movements at CERN or flight routes, using much less power and much less time than conventional simulations even if it's not quite as accurate. It is good at sequence mapping, used in things like cleaning DNA sequences or language translation. And it works for similarity-based generation--creating the next examples of something, such as creating voices, photos, or video.

So it is not obvious that the additional $\alpha$ dependence of $E (\textbf{m}_N)$ that you point out has vanishing derivative, but there it is, it does. I too was puzzled when I saw no mention of it in the text, or in the solution posted for exercise 3.20 asking to deriver the result, which is therefore rather incomplete. A similar thing happens when maximizing the evidence wrt to $\beta$.