We propose a novel model for temporal detection and localization which allows the training of deep neural networks using only counts of event occurrences as training labels. This powerful weakly-supervised framework alleviates the burden of the imprecise and time-consuming process of annotating event locations in temporal data. Unlike existing methods, in which localization is explicitly achieved by design, our model learns localization implicitly as a byproduct of learning to count instances. This unique feature is a direct consequence of the model's theoretical properties. We validate the effectiveness of our approach in a number of experiments (drum hit and piano onset detection in audio, digit detection in images) and demonstrate performance comparable to that of fully-supervised state-of-the-art methods, despite much weaker training requirements.

The effectiveness of biosignal generation and data augmentation with biosignal generative models based on generative adversarial networks (GANs), which are a type of deep learning technique, was demonstrated in our previous paper. GAN-based generative models only learn the projection between a random distribution as input data and the distribution of training data.Therefore, the relationship between input and generated data is unclear, and the characteristics of the data generated from this model cannot be controlled. This study proposes a method for generating time-series data based on GANs and explores their ability to generate biosignals with certain classes and characteristics. Moreover, in the proposed method, latent variables are analyzed using canonical correlation analysis (CCA) to represent the relationship between input and generated data as canonical loadings. Using these loadings, we can control the characteristics of the data generated by the proposed method. The influence of class labels on generated data is analyzed by feeding the data interpolated between two class labels into the generator of the proposed GANs. The CCA of the latent variables is shown to be an effective method of controlling the generated data characteristics. We are able to model the distribution of the time-series data without requiring domain-dependent knowledge using the proposed method. Furthermore, it is possible to control the characteristics of these data by analyzing the model trained using the proposed method. To the best of our knowledge, this work is the first to generate biosignals using GANs while controlling the characteristics of the generated data.

We propose an intriguingly simple method for the construction of adversarial images in the black-box setting. In constrast to the white-box scenario, constructing black-box adversarial images has the additional constraint on query budget, and efficient attacks remain an open problem to date. With only the mild assumption of continuous-valued confidence scores, our highly query-efficient algorithm utilizes the following simple iterative principle: we randomly sample a vector from a predefined orthonormal basis and either add or subtract it to the target image. Despite its simplicity, the proposed method can be used for both untargeted and targeted attacks -- resulting in previously unprecedented query efficiency in both settings. We demonstrate the efficacy and efficiency of our algorithm on several real world settings including the Google Cloud Vision API. We argue that our proposed algorithm should serve as a strong baseline for future black-box attacks, in particular because it is extremely fast and its implementation requires less than 20 lines of PyTorch code.

We design a self size-estimating feed-forward network (SSFN) using a joint optimization approach for estimation of number of layers, number of nodes and learning of weight matrices at a low computational complexity. In the proposed approach, SSFN grows from a small-size network to a large-size network. The increase in size from small-size to large-size guarantees a monotonically decreasing cost with addition of nodes and layers. The optimization approach uses a sequence of layer-wise target-seeking non-convex optimization problems. Using `lossless flow property' of some activation functions, such as rectified linear unit (ReLU), we analytically find regularization parameters in the layer-wise non-convex optimization problems. Closed-form analytic expressions of regularization parameters allow to avoid tedious cross-validations. The layer-wise non-convex optimization problems are further relaxed to convex optimization problems for ease of implementation and analytical tractability. The convex relaxation helps to design a low-complexity algorithm for construction of the SSFN. We experiment with eight popular benchmark datasets for sound and image classification tasks. Using extensive experiments we show that the SSFN can self-estimate its size using the low-complexity algorithm. The size of SSFN varies significantly across the eight datasets.

"We have proposed a new framework for continual learning, which decouples network structure learning and model parameter learning," says Yingbo Zhou, co-lead author of the paper and a research scientist at Salesforce Research. "We call it the Learn to Grow framework. In experimental testing, we've found that it outperforms previous approaches to continual learning." To understand the Learn to Grow framework, think of deep neural networks as a pipe filled with multiple layers. Raw data goes into the top of the pipe, and task outputs come out the bottom.

Deep learning is also known as deep structured learning or hierarchical learning, It is part of a broader family of machine learning methods based on the layers used in artificial neural networks, Deep learning is a subset of the field of machine learning, which is a subfield of AI, Deep learning applications are used in industries from automated driving to medical devices. It is a class of machine learning algorithms that use a cascade of multiple layers of nonlinear processing units for feature extraction and transformation, Each successive layer uses the output from the previous layer as input, It can be learned in supervised (e.g., classification) and/or unsupervised (e.g., pattern analysis) manners, It enables computational models which are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. It is a subfield of machine learning concerned with algorithms inspired by the structure & function of the brain called artificial neural networks, It can teach computers to do what comes naturally to humans: learn by example, Deep learning can be used in driverless cars, allowing them to recognize the stop sign, or to distinguish the pedestrian from the lamppost. The computer model learns to perform classification tasks from images, text, or sound, Deep learning models can achieve state of art accuracy, sometimes exceeding human-level performance, Models are trained by using a large set of labeled data & neural network architectures that have many layers. Neural networks are static & symbolic, They were inspired by information processing & distributed communication nodes in biological systems synaptic structures, they have many differences from the structural & functional properties of biological brains, that make them incompatible with the neurological evidence, while the biological brain of most living organisms is dynamic (plasticity) and analog.

Tech Data on Wednesday said it's partnerubg with Deep Instinct for its end-to-end deep learning framework for cybersecurity. The Deep Instinct platform provides enhanced protection by predicting harmful known and unknown cyberattacks, terminating execution and preventing any possible damage. Tech Data's Alex Ryals "We believe artificial intelligence (AI)-based deep learning tools are the next wave in advanced cyberprotection," said Alex Ryals, vice president of security solutions, Americas, at Tech Data. "Because these tools are autonomous and constantly learning, not only do they require fewer updates, but unlike typical machine […]

Score matching is a popular method for estimating unnormalized statistical models. However, it has been so far limited to simple models or low-dimensional data, due to the difficulty of computing the trace of Hessians for log-density functions. We show this difficulty can be mitigated by sliced score matching, a new objective that matches random projections of the original scores. Our objective only involves Hessian-vector products, which can be easily implemented using reverse-mode auto-differentiation. This enables scalable score matching for complex models and higher dimensional data. Theoretically, we prove the consistency and asymptotic normality of sliced score matching. Moreover, we demonstrate that sliced score matching can be used to learn deep score estimators for implicit distributions. In our experiments, we show that sliced score matching greatly outperforms competitors on learning deep energy-based models, and can produce accurate score estimates for applications such as variational inference with implicit distributions and training Wasserstein Auto-Encoders.

Model compression is eminently suited for deploying deep learning on IoT-devices. However, existing model compression techniques rely on access to the original or some alternate dataset. In this paper, we address the model compression problem when no real data is available, e.g., when data is private. To this end, we propose Dream Distillation, a data-independent model compression framework. Our experiments show that Dream Distillation can achieve 88.5% accuracy on the CIFAR-10 test set without actually training on the original data!

We study the problem of interference source identification, through the lens of recognizing one of 15 different channels that belong to 3 different wireless technologies: Bluetooth, Zigbee, and WiFi. We employ deep learning algorithms trained on received samples taken from a 10 MHz band in the 2.4 GHz ISM Band. We obtain a classification accuracy of around 89.5% using any of four different deep neural network architectures: CNN, ResNet, CLDNN, and LSTM, which demonstrate the generality of the effectiveness of deep learning at the considered task. Interestingly, our proposed CNN architecture requires approximately 60% of the training time required by the state of the art while achieving slightly larger classification accuracy. We then focus on the CNN architecture and further optimize its training time while incurring minimal loss in classification accuracy using three different approaches: 1- Band Selection, where we only use samples belonging to the lower and uppermost 2 MHz bands, 2- SNR Selection, where we only use training samples belonging to a single SNR value, and 3- Sample Selection, where we try various sub-Nyquist sampling methods to select the subset of samples most relevant to the classification task. Our results confirm the feasibility of fast deep learning for wireless interference identification, by showing that the training time can be reduced by as much as 30x with minimal loss in accuracy.