There is a bunch of people that don't really know if there's any difference between in such hyped terms like machine learning and deep learning and how these two are related to each other. Before we go any further, it's worth mentioning that even though AI, ML, and deep learning often times are used instead of one another, especially by some businessmen, marketers or startuppers, but these terms are not all the same! So, please, stop muddle them! To start with, artificial intelligence is a much broader term that encompasses machine learning and its smaller subset of deep learning. Do you see where we're going with this?

An Indian student in the US has created a space-detecting algorithm that can help tackle the problem of finding a parking spot by using big data analytics and save a person's time and money. Sai Nikhil Reddy Mettupally, who is studying at The University of Alabama in Huntsville (UAH), has also won second prize at the 2018 Science and Technology Open House competition for his creation. According to a university press release, Sai's creation relies on big data analytics and deep-learning techniques to lead drivers directly to an empty parking spot. Big data analytics is a complex process of examining large and varied data sets to uncover information including hidden patterns, unknown correlations, market trends and customer preferences. Sai conceived the idea shortly after the university transitioned to zone parking last fall. "The data show that, on a typical day, there is a high chance that students or faculty members will have difficulty getting a parking spot between 11 am and 1 pm, leading to the wastage of time and fuel, and adding to the pollution" He says.

There's a lot of people in the machine learning community who'll tell you that deep learning (DL) is a dead end. He believes DL is just getting started, in fact he says we're about to enter the next phase of AI, and deep learning at the edge is a huge part of that. He probably knows what he's talking about. After all most of the world's AI compute cycles are run on his company's architecture. Singer is Intel's Vice President, Artificial Intelligence Products Group Architecture General Manager. He has the difficult task of figuring out what to do next with the company's AI vision.

Knime (the K is silent, so it's pronounced nīm) is a highly rated data analytics platform with wide applicability and many integrations with other products, such as with databases, languages, machine learning frameworks, and deep learning frameworks. The philosophy of Knime is to be inclusive and "blend" whatever software and data sources you want to use. The exploration, model building, visualization, reporting, and development portions of the platform are open source, as are the community extensions. Knime Server, which provides collaboration, automation, management, and deployment capabilities, is commercial, as are the partner extensions. Knime Analytics Platform and Knime Server are available for on-prem installation and for the AWS and Azure clouds.

Machine learning and deep learning methods are often reported to be the key solution to all predictive modeling problems. An important recent study evaluated and compared the performance of many classical and modern machine learning and deep learning methods on a large and diverse set of more than 1,000 univariate time series forecasting problems. The results of this study suggest that simple classical methods, such as linear methods and exponential smoothing, outperform complex and sophisticated methods, such as decision trees, Multilayer Perceptrons (MLP), and Long Short-Term Memory (LSTM) network models. These findings highlight the requirement to both evaluate classical methods and use their results as a baseline when evaluating any machine learning and deep learning methods for time series forecasting in order demonstrate that their added complexity is adding skill to the forecast. In this post, you will discover the important findings of this recent study evaluating and comparing the performance of a classical and modern machine learning methods on a large and diverse set of time series forecasting datasets.

How to balance accuracy vs explainability of Machine Learning models? Deep Learning methods build very good prediction and classification models, but they are very hard for humans to understand. The European GDPR laws enacted in May 2018, which give consumers some right to explanation of decision made about them by algorithms, and recent story about Amazon scrapping their internal recruiting tool because of bias against women, highlight the importance of understanding Machine Learning models in many areas. New KDnuggets poll below aims to measure the current importance of understanding of ML models. Poll When building Machine Learning / Data Science models in 2018, how often was it important that the model be humanly understandable/explainable?

This paper addresses detection of a reverse engineering (RE) attack targeting a deep neural network (DNN) image classifier; by querying, RE's aim is to discover the classifier's decision rule. RE can enable test-time evasion attacks, which require knowledge of the classifier. Recently, we proposed a quite effective approach (ADA) to detect test-time evasion attacks. In this paper, we extend ADA to detect RE attacks (ADA-RE). We demonstrate our method is successful in detecting "stealthy" RE attacks before they learn enough to launch effective test-time evasion attacks.

Recently, with convolutional neural networks gaining significant achievements in many challenging machine learning fields, hand-crafted neural networks no longer satisfy our requirements as designing a network will cost a lot, and automatically generating architectures has attracted increasingly more attention and focus. Some research on auto-generated networks has achieved promising results. However, they mainly aim at picking a series of single layers such as convolution or pooling layers one by one. There are many elegant and creative designs in the carefully hand-crafted neural networks, such as Inception-block in GoogLeNet, residual block in residual network and dense block in dense convolutional network. Based on reinforcement learning and taking advantages of the superiority of these networks, we propose a novel automatic process to design a multi-block neural network, whose architecture contains multiple types of blocks mentioned above, with the purpose to do structure learning of deep neural networks and explore the possibility whether different blocks can be composed together to form a well-behaved neural network. The optimal network is created by the Q-learning agent who is trained to sequentially pick different types of blocks. To verify the validity of our proposed method, we use the auto-generated multi-block neural network to conduct experiments on image benchmark datasets MNIST, SVHN and CIFAR-10 image classification task with restricted computational resources. The results demonstrate that our method is very effective, achieving comparable or better performance than hand-crafted networks and advanced auto-generated neural networks.

Accurate and reliable traffic forecasting for complicated transportation networks is of vital importance to modern transportation management. The complicated spatial dependencies of roadway links and the dynamic temporal patterns of traffic states make it particularly challenging. To address these challenges, we propose a new capsule network (CapsNet) to extract the spatial features of traffic networks and utilize a nested LSTM (NLSTM) structure to capture the hierarchical temporal dependencies in traffic sequence data. A framework for network-level traffic forecasting is also proposed by sequentially connecting CapsNet and NLSTM. On the basis of literature review, our study is the first to adopt CapsNet and NLSTM in the field of traffic forecasting. An experiment on a Beijing transportation network with 278 links shows that the proposed framework with the capability of capturing complicated spatiotemporal traffic patterns outperforms multiple state-of-the-art traffic forecasting baseline models. The superiority and feasibility of CapsNet and NLSTM are also demonstrated, respectively, by visualizing and quantitatively evaluating the experimental results.

Convolutional neural networks (CNN) have recently achieved state-of-the-art results in various applications. In the case of image recognition, an ideal model has to learn independently of the training data, both local dependencies between the three components (R,G,B) of a pixel, and the global relations describing edges or shapes, making it efficient with small or heterogeneous datasets. Quaternion-valued convolutional neural networks (QCNN) solved this problematic by introducing multidimensional algebra to CNN. This paper proposes to explore the fundamental reason of the success of QCNN over CNN, by investigating the impact of the Hamilton product on a color image reconstruction task performed from a gray-scale only training. By learning independently both internal and external relations and with less parameters than real valued convolutional encoder-decoder (CAE), quaternion convolutional encoder-decoders (QCAE) perfectly reconstructed unseen color images while CAE produced worst and gray-scale versions.