This is a clip from a conversation with Jeremy Howard from Aug 2019. You can watch the full conversation here: https://www.youtube.com/watch?v J6XcP... (more links below) Podcast full episodes playlist: https://www.youtube.com/playlist?list... Podcasts clips playlist: https://www.youtube.com/playlist?list... Podcast website: https://lexfridman.com/ai Note: I select clips with insights from these much longer conversation with the hope of helping make these ideas more accessible and discoverable. Ultimately, this podcast is a small side hobby for me with the goal of sharing and discussing ideas. I did a poll and 92% of people either liked or loved the posting of daily clips, 2% were indifferent, and 6% hated it, some suggesting that I post them on a separate YouTube channel.

From the soaring stock price of NVIDIA, to the cutting-edge developments at Facebook and Google, AI hardware is a hot topic. We set out to learn more about what executives should know about the coming developments in AI hardware – and how it might impact different industries and sectors. In the subsections of the article that follows, we will delve deeper into these questions, highlighting the key insights from the professionals we corresponded with. AI software has always received the lion's share of attention, but as the computational resources needed to process this software soar exponentially, a new generation of AI chips is coming into being. Developments in AI hardware will take the spotlight, as companies converge at the AI Hardware Summit September.

Many think we'll see human-level artificial intelligence in the next 10 years. Industry continues to boast smarter tech like personalized assistants or self-driving cars. And in computer science, new and powerful tools embolden researchers to assert that we are nearing the goal in the quest for human-level artificial intelligence. Despite the hype, despite progress, we are far from machines that think like you and me. Last year Google unveiled Duplex -- a Pixel smartphone assistant which can call and make reservations for you.

Generative Adversarial Networks have been shown to be powerful in generating content. To this end, they have been studied intensively in the last few years. Nonetheless, training these networks requires solving a saddle point problem that is difficult to solve and slowly converging. Motivated from techniques in the registration of point clouds and by the fluid flow formulation of mass transport, we investigate a new formulation that is based on strict minimization, without the need for the maximization. The formulation views the problem as a matching problem rather than an adversarial one and thus allows us to quickly converge and obtain meaningful metrics in the optimization path.

The study presents a numerical model of leaky integrate-and-fire neuron created on the basis of $VO_2$ switch. The analogue of the membrane potential in the model is the temperature of the switch channel, and the action potential from neighbouring neurons propagates along the substrate in the form of thermal pulses. We simulated the operation of three neurons and demonstrated that the total effect happens due to interference of thermal waves in the region of the neuron switching channel. The thermal mechanism of the threshold function operates due to the effect of electrical switching, and the magnitude (temperature) of the threshold can vary by external voltage. The neuron circuit does not contain capacitor, making it possible to produce a network with a high density of components, and has the potential for 3D integration due to the thermal mechanism of neurons interaction.

Multi-label classification (MLC) is an important class of machine learning problems that come with a wide spectrum of applications, each demanding a possibly different evaluation criterion. When solving the MLC problems, we generally expect the learning algorithm to take the hidden correlation of the labels into account to improve the prediction performance. Extracting the hidden correlation is generally a challenging task. In this work, we propose a novel deep learning framework to better extract the hidden correlation with the help of the memory structure within recurrent neural networks. The memory stores the temporary guesses on the labels and effectively allows the framework to rethink about the goodness and correlation of the guesses before making the final prediction. Furthermore, the rethinking process makes it easy to adapt to different evaluation criteria to match real-world application needs. In particular, the framework can be trained in an end-to-end style with respect to any given MLC evaluation criteria. The end-to-end design can be seamlessly combined with other deep learning techniques to conquer challenging MLC problems like image tagging. Experimental results across many real-world data sets justify that the rethinking framework indeed improves MLC performance across different evaluation criteria and leads to superior performance over state-of-the-art MLC algorithms.

Machine-learned diagnosis models have shown promise as medical aides but are trained under a closed-set assumption, i.e. that models will only encounter conditions on which they have been trained. However, it is practically infeasible to obtain sufficient training data for every human condition, and once deployed such models will invariably face previously unseen conditions. We frame machine-learned diagnosis as an open-set learning problem, and study how state-of-the-art approaches compare. Further, we extend our study to a setting where training data is distributed across several healthcare sites that do not allow data pooling, and experiment with different strategies of building open-set diagnostic ensembles. Across both settings, we observe consistent gains from explicitly modeling unseen conditions, but find the optimal training strategy to vary across settings.

Fraud causes substantial costs and losses for companies and clients in the finance and insurance industries. Examples are fraudulent credit card transactions or fraudulent claims. It has been estimated that roughly $10$ percent of the insurance industry's incurred losses and loss adjustment expenses each year stem from fraudulent claims. The rise and proliferation of digitization in finance and insurance have lead to big data sets, consisting in particular of text data, which can be used for fraud detection. In this paper, we propose architectures for text embeddings via deep learning, which help to improve the detection of fraudulent claims compared to other machine learning methods. We illustrate our methods using a data set from a large international health insurance company. The empirical results show that our approach outperforms other state-of-the-art methods and can help make the claims management process more efficient. As (unstructured) text data become increasingly available to economists and econometricians, our proposed methods will be valuable for many similar applications, particularly when variables have a large number of categories as is typical for example of the International Classification of Disease (ICD) codes in health economics and health services.

Cell detection and cell type classification from biomedical images play an important role for high-throughput imaging and various clinical application. While classification of single cell sample can be performed with standard computer vision and machine learning methods, analysis of multi-label samples (region containing congregating cells) is more challenging, as separation of individual cells can be difficult (e.g. touching cells) or even impossible (e.g. overlapping cells). As multi-instance images are common in analyzing Red Blood Cell (RBC) for Sickle Cell Disease (SCD) diagnosis, we develop and implement a multi-instance cell detection and classification framework to address this challenge. The framework firstly trains a region proposal model based on Region-based Convolutional Network (RCNN) to obtain bounding-boxes of regions potentially containing single or multiple cells from input microscopic images, which are extracted as image patches. High-level image features are then calculated from image patches through a pre-trained Convolutional Neural Network (CNN) with ResNet-50 structure. Using these image features inputs, six networks are then trained to make multi-label prediction of whether a given patch contains cells belonging to a specific cell type. As the six networks are trained with image patches consisting of both individual cells and touching/overlapping cells, they can effectively recognize cell types that are presented in multi-instance image samples. Finally, for the purpose of SCD testing, we train another machine learning classifier to predict whether the given image patch contains abnormal cell type based on outputs from the six networks. Testing result of the proposed framework shows that it can achieve good performance in automatic cell detection and classification.

Though they become the most representative intelligent systems with a dominant performance, DNNs are criticized for lacking transparency and interpretability. Better understanding the working mechanism of machine learning systems has become a requested demand, which is not only beneficial to academic research but also significant to many critical industries requiring a high level of safety concerns. In this paper, we propose a simple and interpretable disentanglement form for deep neural networks, which can not only reveal neural network's functional behaviors but also have application improvement in visual explanation task [8] and adversarial example detection [1]. The main idea is that we propose to extract the class-specific sub-network for each semantic category from a pre-trained full Figure 1: Method overview. For each class, we extract a subnetwork from the full model by learning to activate only a fraction of neurons on each layer. The extracted class-specific subnetwork can focus on one class prediction, and maintain comparable performance with the full model.