Epilepsy is one of the most common neurological disorders, affecting about 1% of the population at all ages. Detecting the development of epilepsy, i.e., epileptogenesis (EPG), before any seizures occur could allow for early interventions and potentially more effective treatments. Here, we investigate if modern machine learning (ML) techniques can detect EPG from intra-cranial electroencephalography (EEG) recordings prior to the occurrence of any seizures. For this we use a rodent model of epilepsy where EPG is triggered by electrical stimulation of the brain. We propose a ML framework for EPG identification, which combines a deep convolutional neural network (CNN) with a prediction aggregation method to obtain the final classification decision. Specifically, the neural network is trained to distinguish five second segments of EEG recordings taken from either the pre-stimulation period or the post-stimulation period. Due to the gradual development of epilepsy, there is enormous overlap of the EEG patterns before and after the stimulation. Hence, a prediction aggregation process is introduced, which pools predictions over a longer period. By aggregating predictions over one hour, our approach achieves an area under the curve (AUC) of 0.99 on the EPG detection task. This demonstrates the feasibility of EPG prediction from EEG recordings.

It is hard to train Recurrent Neural Network (RNN) with stable convergence and avoid gradient vanishing and exploding, as the weights in the recurrent unit are repeated from iteration to iteration. Moreover, RNN is sensitive to the initialization of weights and bias, which brings difficulty in the training phase. With the gradient-free feature and immunity to poor conditions, the Alternating Direction Method of Multipliers (ADMM) has become a promising algorithm to train neural networks beyond traditional stochastic gradient algorithms. However, ADMM could not be applied to train RNN directly since the state in the recurrent unit is repetitively updated over timesteps. Therefore, this work builds a new framework named ADMMiRNN upon the unfolded form of RNN to address the above challenges simultaneously and provides novel update rules and theoretical convergence analysis. We explicitly specify key update rules in the iterations of ADMMiRNN with deliberately constructed approximation techniques and solutions to each subproblem instead of vanilla ADMM. Numerical experiments are conducted on MNIST and text classification tasks, where ADMMiRNN achieves convergent results and outperforms compared baselines. Furthermore, ADMMiRNN trains RNN in a more stable way without gradient vanishing or exploding compared to the stochastic gradient algorithms. Source code has been available at https://github.com/TonyTangYu/ADMMiRNN.

Classifying sequential data as early as and as accurately as possible is a challenging yet critical problem, especially when a sampling cost is high. One algorithm that achieves this goal is the sequential probability ratio test (SPRT), which is known as Bayes-optimal: it can keep the expected number of data samples as small as possible, given the desired error upper-bound. The SPRT has recently been found to be the best model that explains the activities of the neurons in the primate parietal cortex that are thought to mediate our complex decision-making processes. However, the original SPRT makes two critical assumptions that limit its application in real-world scenarios: (i) samples are independently and identically distributed, and (ii) the likelihood of the data being derived from each class can be calculated precisely. Here, we propose the SPRT-TANDEM, a deep neural network-based SPRT algorithm that overcomes the above two obstacles. The SPRT-TANDEM estimates the log-likelihood ratio of two alternative hypotheses by leveraging a novel Loss function for Log-Likelihood Ratio estimation (LLLR), while allowing for correlations up to $N (\in \mathbb{N})$ preceding samples. In tests on one original and two public video databases, Nosaic MNIST, UCF101, and SiW, the SPRT-TANDEM achieves statistically significantly better classification accuracy than other baseline classifiers, with a smaller number of data samples. The code and Nosaic MNIST are publicly available at https://github.com/TaikiMiyagawa/SPRT-TANDEM.

Stitching a patient back together after surgery is a vital but monotonous task for medics, often requiring them to repeat the same simple movements over and over hundreds of times. But thanks to a collaborative effort between Intel and the University of California, Berkeley, tomorrow's surgeons could offload that grunt work to robots -- like a macro, but for automated suturing. The UC Berkeley team, led by Dr. Ajay Tanwani, has developed a semi-supervised AI deep-learning system, dubbed Motion2Vec. This system is designed to watch publically surgical videos performed by actual doctors, break down the medic's movements when suturing (needle insertion, extraction and hand-off) and then mimic them with a high degree of accuracy. "There's a lot of appeal in learning from visual observations, compared to traditional interfaces for learning in a static way or learning from [mimicking] trajectories, because of the huge amount of information content available in existing videos," Tanwani told Engadget.

Climate change impact studies are subject to numerous uncertainties and assumptions. One of the main sources of uncertainty arises from the interpretation of climate model projections. Probabilistic procedures based on multimodel ensembles have been suggested in the literature to quantify this source of uncertainty. However, the interpretation of multimodel ensembles remains challenging. Several ... [Show full abstract] assumptions are often required in the uncertainty quantification of climate model projections.

From navigating to a new place to picking out new music, algorithms have laid the foundation for large parts of modern life. Similarly, artificial intelligence is booming because it automates and backs so many products and applications. Recently, I addressed some analytical applications for TensorFlow. In this article, I'm going to lay out a higher-level view of Google's TensorFlow deep learning framework, with the ultimate goal of helping you to understand and build deep learning algorithms from scratch. Over the past couple of decades, deep learning has evolved rapidly, leading to massive disruption in a range of industries and organizations. The term was coined in 1943 when Warren McCulloch and Walter Pitts created a computer model based on neural networks of a human brain, creating the first artificial neural networks (or ANNs). Backpropagation is a popular algorithm that has had a huge impact in the field of deep learning.

In the race to enable manufacturing plants to increase production in the face of an intermittent human workforce, manufacturers are looking at how to supplement their cameras with AI to give human inspectors the ability to spot defective products immediately and correct the problem. While machine vision has been around for more than 60 years, the recent surge in the popularity of deep learning has elevated this sometimes misunderstood technology to the attention of major manufacturers globally. As CEO of a deep learning software company, I've seen how deep learning is a natural next step from machine vision, and has the potential to drive innovation for manufacturers. How does deep learning differ from machine vision, and how can manufacturers leverage this natural evolution of camera technology to cope with real-world demands? In the 1960s, several groups of scientists, many of them in the Boston area, set forth to solve "the machine vision problem."

Tensorflow, developed by the Google brain team in 2015, is the most popular framework for deep learning. This is largely due to its support for multiple languages, Tensorflow is written in C, but you can interact with it through Python, Javascript, Go and R. In addition to its flexible architecture and scalability (models can be trained on both GPU's and CPU's and deployed through a web service, desktop application or on a mobile device). This article is a complete beginners guide to this tool. It is not meant as an in-depth introduction but instead is designed to get you up and running to develop your first deep learning model. In my opinion, it is difficult to find deep learning tutorials that don't include a lot of complexity and heavy math.

Activation functions play a major role in the learning process of a neural network. So far, we have used only the sigmoid function as the activation function in our networks, but we saw how the sigmoid function has its shortcomings since it can lead to the vanishing gradient problem for the earlier layers. In this blog, we will discuss other activation functions; ones that are more efficient to use and are more applicable to deep learning applications. There are seven types of activation functions that you can use when building a neural network. There is the binary step function, the linear or identity function, there is our old friend the sigmoid or logistic function, there is the hyperbolic tangent, or tanh, function, the rectified linear unit (ReLU) function, the leaky ReLU function, and the softmax function.

Training and testing deep learning models is a difficult process that requires sophisticated knowledge of machine learning and data infrastructures. From feature modeling to hyperparameter optimization, the processes for training and testing deep learning models are one of the biggest bottlenecks in data science solutions in the real world. Simplifying this element could help to streamline the adoption of deep learning technologies. While the low-code training of deep learning models is a nascent space, we are already seeing relevant innovations. One of the most complete solutions to tackle that problem came from Uber AI Labs.