Machine learning is an incredibly broad and diverse field, with a non-stop increase on research, along a multitude of applications. Thus writing a list enlisting the best machine learning researchers on the field proves challenging for a number of reasons. Please mind that this list encompasses researchers who are currently working on the field. Also, please mind that this list is by no means ranked. Everyone listed below has done extraordinary work to advance humanity's state of AI further.

As part of the MIT Deep Learning series of lectures and GitHub tutorials, we are covering the basics of using neural networks to solve problems in computer vision, natural language processing, games, autonomous driving, robotics, and beyond. This blog post provides an overview of deep learning in 7 architectural paradigms with links to TensorFlow tutorials for each. It accompanies the following lecture on Deep Learning Basics as part of MIT course 6.S094: Deep learning is representation learning: the automated formation of useful representations from data. How we represent the world can make the complex appear simple both to us humans and to the machine learning models we build. My favorite example of the former is the publication in 1543 by Copernicus of the heliocentric model that put the Sun at the center of the "Universe" as opposed to the prior geocentric model that put the Earth at the center.

Despite how groundbreaking artificial intelligence may seem today, it isn't a new phenomenon. The technology and the concept have existed since the 1950's. It was 1956 when AI was first studied at the Dartmouth Summer Research Project on Artificial Intelligence. Around the 1960's and 1970's, AI advanced rapidly. We saw the invention of anthropomorphic and autonomous robots.

As part of the commitment to continuous (& cutting edge) research at Razorthink Inc, we are coming up with a series of review papers which will screen through the best of research done in the field of deep learning, machine learning, data science and artificial intelligence in general, across the globe. Each week, we will pick up one research paper, break it down to make it easier to understand, take you through the entire research approach, major takeaways and finally bring in the applicability in real use-cases. Our first pick in the series is "Distilling a Neural Network into a soft decision tree" (download link at the bottom) originally written by Nicholas Frosst & Geoffrey Hinton (Google Brain Team). Deep Neural networks have been proven to be very effective in performing tasks that involve classification and prediction based on the complexity of the data. Most importantly, it is highly useful in situations where the input data has a complex relationship with the target variable and the dimensions of the input data is very high.

Real-time recognition of dynamic hand gestures from video streams is a challenging task since (i) there is no indication when a gesture starts and ends in the video, (ii) performed gestures should only be recognized once, and (iii) the entire architecture should be designed considering the memory and power budget. In this work, we address these challenges by proposing a hierarchical structure enabling offline-working convolutional neural network (CNN) architectures to operate online efficiently by using sliding window approach. The proposed architecture consists of two models: (1) A detector which is a lightweight CNN architecture to detect gestures and (2) a classifier which is a deep CNN to classify the detected gestures. In order to evaluate the single-time activations of the detected gestures, we propose to use Levenshtein distance as an evaluation metric since it can measure misclassifications, multiple detections, and missing detections at the same time. We evaluate our architecture on two publicly available datasets - EgoGesture and NVIDIA Dynamic Hand Gesture Datasets - which require temporal detection and classification of the performed hand gestures. ResNeXt-101 model, which is used as a classifier, achieves the state-of-the-art offline classification accuracy of 94.04% and 83.82% for depth modality on EgoGesture and NVIDIA benchmarks, respectively. In real-time detection and classification, we obtain considerable early detections while achieving performances close to offline operation. The codes and pretrained models used in this work are publicly available.

In this paper, we argue that simulation platforms enable a novel type of embodied spatial reasoning, one facilitated by a formal model of object and event semantics that renders the continuous quantitative search space of an open-world, real-time environment tractable. We provide examples for how a semantically-informed AI system can exploit the precise, numerical information provided by a game engine to perform qualitative reasoning about objects and events, facilitate learning novel concepts from data, and communicate with a human to improve its models and demonstrate its understanding. We argue that simulation environments, and game engines in particular, bring together many different notions of "simulation" and many different technologies to provide a highly-effective platform for developing both AI systems and tools to experiment in both machine and human intelligence.

This is an integrative review that address the question, "What makes for a good explanation?" with reference to AI systems. Pertinent literatures are vast. Thus, this review is necessarily selective. That said, most of the key concepts and issues are expressed in this Report. The Report encapsulates the history of computer science efforts to create systems that explain and instruct (intelligent tutoring systems and expert systems). The Report expresses the explainability issues and challenges in modern AI, and presents capsule views of the leading psychological theories of explanation. Certain articles stand out by virtue of their particular relevance to XAI, and their methods, results, and key points are highlighted. It is recommended that AI/XAI researchers be encouraged to include in their research reports fuller details on their empirical or experimental methods, in the fashion of experimental psychology research reports: details on Participants, Instructions, Procedures, Tasks, Dependent Variables (operational definitions of the measures and metrics), Independent Variables (conditions), and Control Conditions.

When deep neural networks optimize highly complex functions, it is not always obvious how they reach the final decision. Providing explanations would make this decision process more transparent and improve a user's trust towards the machine as they help develop a better understanding of the rationale behind the network's predictions. Here, we present an explainable observer-classifier framework that exposes the steps taken through the model's decision-making process. Instead of assigning a label to an image in a single step, our model makes iterative binary sub-decisions, which reveal a decision tree as a thought process. In addition, our model allows to hierarchically cluster the data and give each binary decision a semantic meaning. The sequence of binary decisions learned by our model imitates human-annotated attributes. On six benchmark datasets with increasing size and granularity, our model outperforms the decision-tree baseline and generates easy-to-understand binary decision sequences explaining the network's predictions.

In low light or short-exposure photography the image is often corrupted by noise. While longer exposure helps reduce the noise, it can produce blurry results due to the object and camera motion. The reconstruction of a noise-less image is an ill posed problem. Recent approaches for image denoising aim to predict kernels which are convolved with a set of successively taken images (burst) to obtain a clear image. We propose a deep neural network based approach called Multi-Kernel Prediction Networks (MKPN) for burst image denoising. MKPN predicts kernels of not just one size but of varying sizes and performs fusion of these different kernels resulting in one kernel per pixel. The advantages of our method are two fold: (a) the different sized kernels help in extracting different information from the image which results in better reconstruction and (b) kernel fusion assures retaining of the extracted information while maintaining computational efficiency. Experimental results reveal that MKPN outperforms state-of-the-art on our synthetic datasets with different noise levels.

Many post-disaster and -conflict regions do not have sufficient data on their transportation infrastructure assets, hindering both mobility and reconstruction. In particular, as the number of aging and deteriorating bridges increase, it is necessary to quantify their load characteristics in order to inform maintenance and prevent failure. The load carrying capacity and the design load are considered as the main aspects of any civil structures. Human examination can be costly and slow when expertise is lacking in challenging scenarios. In this paper, we propose to employ deep learning as method to estimate the load carrying capacity from crowd sourced images. A new convolutional neural network architecture is trained on data from over 6000 bridges, which will benefit future research and applications. We tackle significant variations in the dataset (e.g. class interval, image completion, image colour) and quantify their impact on the prediction accuracy, precision, recall and F1 score. Finally, practical optimisation is performed by converting multiclass classification into binary classification to achieve a promising field use performance.