Artificial Intelligence (AI) is being used more and more by chemists to perform various tasks. Originally, research in AI applied to chemistry has largely been fueled by the need to accelerate drug discovery and reduce its huge costs and the time to market for new drugs. So far, AI has made significant progess towards the acceleration of drug discovery R&D. However, the applications of AI in chemistry are not limited to drug discovery, as discussed in a recent review. In this article, we will provide a general picture of how AI can help chemists be faster and more creative in their research.

We demonstrate that it is possible to use deep neural networks to produce tomographic reconstructions of dense layered objects with small illumination angle as low as 10 . It is also shown that a DNN trained on synthetic data can generalize well to and produce reconstructions from experimental measurements. This work has application in the field of X-ray tomography for the inspection of integrated circuits and other materials studies. We present a machine learning-based method for tomographic reconstruction of dense layered objects, with range of projection angles limited to 10 . Whereas previous approaches to phase tomography generally require 2 steps, first to retrieve phase projections from intensity projections and then to perform tomographic reconstruction on the retrieved phase projections, in our work a physics-informed preprocessor followed by a deep neural network (DNN) conduct the 3-dimensional reconstruction directly from the intensity projections. We demonstrate this single-step method experimentally in the visible optical domain on a scaled-up integrated circuit phantom. We show that even under conditions of highly attenuated photon fluxes a DNN trained only on synthetic data can be used to successfully reconstruct physical samples disjoint from the synthetic training set. Thus, the need for producing a large number of physical examples for training is ameliorated. The method is generally applicable to tomography with electromagnetic or other types of radiation at all bands. Tomography is the quintessential inverse problem.

Working as a Research Assistant under Professor Gordon Gao, at the University of Maryland, I have had the opportunity to combine both my Data Engineering and Science interests to automate machine learning models in the cloud. Assisting one of Professor Gao's Phd fellows, I was tasked with providing an AWS-based solution, which would reduce human interventions when running a deep learning model for an upcoming health startup. "Reduce Costs of EC2 instances, by running them only for computations, these computations happen whenever a customer uploads data into an S3 bucket, which can be anytime during the day." The computations mentioned encompass the machine learning model and processing data uploaded in S3. This meant, the EC2 should only be run for executing the ML model and should be switched off at other times, also these jobs don't have a fixed time and, the only fixed property they possess is that they have to be run as soon as the data is uploaded into the S3 Data bucket.

Follow along with the code in the directory ml-class / videos / cnn. For setup instructions, check our Getting Started page.

Recently no day goes by without a publication of a new outstanding machine learning application, most likely powered by some deep learning model. At the latest when it supports critical decision-making, you should think about the degree of certainty that comes with every prediction. We will go through why that is, how to define uncertainty and eventually look at some code examples so that you will be able to apply our findings in your next project. Let's do a thought experiment. Imagine you're a company that organizes safaris, and you want to create a safer experience for clients in their adventures.

Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples raises our concerns in adopting deep learning to safety-critical applications. As a result, we have witnessed increasing interests in studying attack and defense mechanisms for DNN models on different data types, such as images, graphs and text. Thus, it is necessary to provide a systematic and comprehensive overview of the main threats of attacks and the success of corresponding countermeasures. In this survey, we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples, for three most popular data types, including images, graphs and text.

We propose K-TanH, a novel, highly accurate, hardware efficient approximation of popular activation function Tanh for Deep Learning. K-TanH consists of a sequence of parameterized bit/integer operations, such as, masking, shift and add/subtract (no floating point operation needed) where parameters are stored in a very small look-up table. The design of K-TanH is flexible enough to deal with multiple numerical formats, such as, FP32 and BFloat16. High quality approximations to other activation functions, e.g., Swish and GELU, can be derived from K-TanH. We provide RTL design for K-TanH to demonstrate its area/power/performance efficacy. It is more accurate than existing piecewise approximations for Tanh. For example, K-TanH achieves $\sim 5\times$ speed up and $> 6\times$ reduction in maximum approximation error over software implementation of Hard TanH. Experimental results for low-precision BFloat16 training of language translation model GNMT on WMT16 data sets with approximate Tanh and Sigmoid obtained via K-TanH achieve similar accuracy and convergence as training with exact Tanh and Sigmoid.

We propose a method for sim-to-real robot learning which exploits simulator state information in a way that scales to many objects. First, we train a pair of encoders on raw object pose targets to learn representations that accurately capture the state information of a multi-object environment. Second, we use these encoders in a reinforcement learning algorithm to train image-based policies capable of manipulating many objects. Our pair of encoders consists of one which consumes RGB images and is used in our policy network, and one which directly consumes a set of raw object poses and is used for reward calculation and value estimation. We evaluate our method on the task of pushing a collection of objects to desired tabletop regions. Compared to methods which rely only on images or use fixed-length state encodings, our method achieves higher success rates, performs well in the real world without fine tuning, and generalizes to different numbers and types of objects not seen during training.

We consider efficiency in the implementation of deep neural networks. Hardware accelerators are gaining interest as machine learning becomes one of the drivers of high-performance computing. In these accelerators, the directed graph describing a neural network can be implemented as a directed graph describing a Boolean circuit. We make this observation precise, leading naturally to an understanding of practical neural networks as discrete functions, and show that so-called binarised neural networks are functionally complete. In general, our results suggest that it is valuable to consider Boolean circuits as neural networks, leading to the question of which circuit topologies are promising. We argue that continuity is central to generalisation in learning, explore the interaction between data coding, network topology, and node functionality for continuity, and pose some open questions for future research. As a first step to bridging the gap between continuous and Boolean views of neural network accelerators, we present some recent results from our work on LUTNet, a novel Field-Programmable Gate Array inference approach. Finally, we conclude with additional possible fruitful avenues for research bridging the continuous and discrete views of neural networks.

Dynamic assessment of patient status (e.g. by an automated, continuously updated assessment of outcome) in the Intensive Care Unit (ICU) is of paramount importance for early alerting, decision support and resource allocation. Extraction and cleaning of expert-selected clinical variables discards information and protracts collaborative efforts to introduce machine learning in medicine. We present improved aggregation methods for a flexible deep learning architecture which learns a joint representation of patient chart, lab and output events. Our models outperform recent deep learning models for patient mortality classification using ICU timeseries, by embedding and aggregating all events with no pre-processing or variable selection. Our model achieves a strong performance of AUROC 0.87 at 48 hours on the MIMIC-III dataset while using 13,233 unique un-preprocessed variables in an interpretable manner via hourly softmax aggregation. This demonstrates how our method can be easily combined with existing electronic health record systems for automated, dynamic patient risk analysis.