Classic supervised learning makes the closed-world assumption, meaning that classes seen in testing must have been seen in training. However, in the dynamic world, new or unseen class examples may appear constantly. A model working in such an environment must be able to reject unseen classes (not seen or used in training). If enough data is collected for the unseen classes, the system should incrementally learn to accept/classify them. This learning paradigm is called open-world learning (OWL). Existing OWL methods all need some form of re-training to accept or include the new classes in the overall model. In this paper, we propose a meta-learning approach to the problem. Its key novelty is that it only needs to train a meta-classifier, which can then continually accept new classes when they have enough labeled data for the meta-classifier to use, and also detect/reject future unseen classes. No re-training of the meta-classifier or a new overall classifier covering all old and new classes is needed. In testing, the method only uses the examples of the seen classes (including the newly added classes) on-the-fly for classification and rejection. Experimental results demonstrate the effectiveness of the new approach.

Recently, Deep Learning has been showing promising results in various Artificial Intelligence applications like image recognition, natural language processing, language modeling, neural machine translation, etc. Although, in general, it is computationally more expensive as compared to classical machine learning techniques, their results are found to be more effective in some cases. Therefore, in this paper, we investigated and compared one of the Deep Learning Architecture called Deep Neural Network (DNN) with the classical Random Forest (RF) machine learning algorithm for the malware classification. We studied the performance of the classical RF and DNN with 2, 4 & 7 layers architectures with the four different feature sets, and found that irrespective of the features inputs, the classical RF accuracy outperforms the DNN.

We investigate a Deep Learning based system for malware detection. In the investigation, we experiment with different combination of Deep Learning architectures including Auto-Encoders, and Deep Neural Networks with varying layers over Malicia malware dataset on which earlier studies have obtained an accuracy of (98%) with an acceptable False Positive Rates (1.07%). But these results were done using extensive man-made custom domain features and investing corresponding feature engineering and design efforts. In our proposed approach, besides improving the previous best results (99.21% accuracy and a False Positive Rate of 0.19%) indicates that Deep Learning based systems could deliver an effective defense against malware. Since it is good in automatically extracting higher conceptual features from the data, Deep Learning based systems could provide an effective, general and scalable mechanism for detection of existing and unknown malware.

Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless, such methods usually require laborious object-level annotations (i.e., object labels and bounding boxes) for effective learning of the object-level visual features. In this paper, we propose a novel and efficient deep framework to boost multi-label classification by distilling knowledge from weakly-supervised detection task without bounding box annotations. Specifically, given the image-level annotations, (1) we first develop a weakly-supervised detection (WSD) model, and then (2) construct an end-to-end multi-label image classification framework augmented by a knowledge distillation module that guides the classification model by the WSD model according to the class-level predictions for the whole image and the object-level visual features for object RoIs. The WSD model is the teacher model and the classification model is the student model. After this cross-task knowledge distillation, the performance of the classification model is significantly improved and the efficiency is maintained since the WSD model can be safely discarded in the test phase. Extensive experiments on two large-scale datasets (MS-COCO and NUS-WIDE) show that our framework achieves superior performances over the state-of-the-art methods on both performance and efficiency.

Understanding the coordinated activity underlying brain computations requires large-scale, simultaneous recordings from distributed neuronal structures at a cellular-level resolution. One major hurdle to design high-bandwidth, high-precision, large-scale neural interfaces lies in the formidable data streams that are generated by the recorder chip and need to be online transferred to a remote computer. The data rates can require hundreds to thousands of I/O pads on the recorder chip and power consumption on the order of Watts for data streaming alone. We developed a deep learning-based compression model to reduce the data rate of multichannel action potentials. The proposed model is built upon a deep compressive autoencoder (CAE) with discrete latent embeddings. The encoder is equipped with residual transformations to extract representative features from spikes, which are mapped into the latent embedding space and updated via vector quantization (VQ). The decoder network reconstructs spike waveforms from the quantized latent embeddings. Experimental results show that the proposed model consistently outperforms conventional methods by achieving much higher compression ratios (20-500x) and better or comparable reconstruction accuracies. Testing results also indicate that CAE is robust against a diverse range of imperfections, such as waveform variation and spike misalignment, and has minor influence on spike sorting accuracy. Furthermore, we have estimated the hardware cost and real-time performance of CAE and shown that it could support thousands of recording channels simultaneously without excessive power/heat dissipation. The proposed model can reduce the required data transmission bandwidth in large-scale recording experiments and maintain good signal qualities. The code of this work has been made available at https://github.com/tong-wu-umn/spike-compression-autoencoder

Yes, both hyperparameter tuning and architecture selection are optimization problems. Whether these are actually less difficult than NN training is debatable -- I think there are as around many papers on new architectures than there are on optimization techniques. Certainly, they are easier in the sense that a human can manually tune parameters and select an architecture which works reasonably well, but not select NN weights. Optimizing deep graphical models such as deep boltzmann machines is probably a more difficult optimization problem than training a neural network, depending on whether you consider DBMs a type of neural network.

Recently, google launched a Dataset search – which is a great resource to find Datasets. In this post, I list some IoT datasets which can be used for Machine Learning or Deep Learning applications. But finding datasets is only part of the story. A static dataset for IoT is not enough i.e. some of the interesting analysis is in streaming mode. To create an end to end streaming implementation from a given dataset, we need knowledge of full stack skills.

Understandably, there is much concern surrounding the lack of transparency in machine learning practices. AlgorithmWatch, a non-profit research and advocacy group, was founded to address those concerns. This group works specifically to evaluate and increase the transparency of algorithmic decisions with social relevance. They network with experts from a variety of cultures and disciplines to explain this complex subject to the general public and develop strategies to mitigate the effects of bias in algorithmic decision making. This fledgling industry will require regulation and purposeful strategies to avoid the danger of bias in the algorithms themselves, and their training data.

Understandably, there is much concern surrounding the lack of transparency in machine learning practices. AlgorithmWatch, a non-profit research and advocacy group, was founded to address those concerns. This group works specifically to evaluate and increase the transparency of algorithmic decisions with social relevance. They network with experts from a variety of cultures and disciplines to explain this complex subject to the general public and develop strategies to mitigate the effects of bias in algorithmic decision making. This fledgling industry will require regulation and purposeful strategies to avoid the danger of bias in the algorithms themselves, and their training data.

This project contains examples which demonstrate how to deploy analytic models to mission-critical, scalable production leveraging Apache Kafka and its Streams API. Examples will include analytic models built with TensorFlow, Keras, H2O, Python, DeepLearning4J and other technologies. More sophisticated use cases around Kafka Streams and other technologies will be added over time. The code is developed and tested on Mac and Linux operating systems. As Kafka does not support and work well on Windows, this is not tested at all.