Gradient-only line searches (GOLS) adaptively determine step sizes along search directions for discontinuous loss functions resulting from dynamic mini-batch sub-sampling in neural network training. Step sizes in GOLS are determined by localizing Stochastic Non-Negative Associated Gradient Projection Points (SNN-GPPs) along descent directions. These are identified by a sign change in the directional derivative from negative to positive along a descent direction. Activation functions are a significant component of neural network architectures as they introduce non-linearities essential for complex function approximations. The smoothness and continuity characteristics of the activation functions directly affect the gradient characteristics of the loss function to be optimized. Therefore, it is of interest to investigate the relationship between activation functions and different neural network architectures in the context of GOLS. We find that GOLS are robust for a range of activation functions, but sensitive to the Rectified Linear Unit (ReLU) activation function in standard feedforward architectures. The zero-derivative in ReLU's negative input domain can lead to the gradient-vector becoming sparse, which severely affects training. We show that implementing architectural features such as batch normalization and skip connections can alleviate these difficulties and benefit training with GOLS for all activation functions considered.

Multi-spectral satellite imaging sensors acquire various spectral band images such as red (R), green (G), blue (B), near-infrared (N), etc. Thanks to the unique spectroscopic property of each spectral band with respective to the objects on the ground, multi-spectral satellite imagery can be used for various geological survey applications. Unfortunately, image artifacts from imaging sensor noises often affect the quality of scenes and have negative impacts on the applications of satellite imagery. Recently, deep learning approaches have been extensively explored for the removal of noises in satellite imagery. Most deep learning denoising methods, however, follow a supervised learning scheme, which requires matched noisy image and clean image pairs that are difficult to collect in real situations. In this paper, we propose a novel unsupervised multispectral denoising method for satellite imagery using wavelet subband cycle-consistent adversarial network (WavCycleGAN). The proposed method is based on unsupervised learning scheme using adversarial loss and cycle-consistency loss to overcome the lack of paired data. Moreover, in contrast to the standard image domain cycleGAN, we introduce a wavelet subband domain learning scheme for effective denoising without sacrificing high frequency components such as edges and detail information. Experimental results for the removal of vertical stripe and wave noises in satellite imaging sensors demonstrate that the proposed method effectively removes noises and preserves important high frequency features of satellite images.

Adversarial training is a popular method to give neural nets robustness against adversarial perturbations. In practice adversarial training leads to low robust training loss. However, a rigorous explanation for why this happens under natural conditions is still missing. Recently a convergence theory for standard (non-adversarial) supervised training was developed by various groups for {\em very overparametrized} nets. It is unclear how to extend these results to adversarial training because of the min-max objective. Recently, a first step towards this direction was made by Gao et al. using tools from online learning, but they require the width of the net to be \emph{exponential} in input dimension $d$, and with an unnatural activation function. Our work proves convergence to low robust training loss for \emph{polynomial} width instead of exponential, under natural assumptions and with the ReLU activation. Key element of our proof is showing that ReLU networks near initialization can approximate the step function, which may be of independent interest.

Learning from Observation (LfO), also known as Behavioral Cloning, is an approach for building software agents by recording the behavior of an expert (human or artificial) and using the recorded data to generate the required behavior. jLOAF is a platform that uses Case-Based Reasoning to achieve LfO. In this paper we interface jLOAF with the popular OpenAI Gym environment. Our experimental results show how our approach can be used to provide a baseline for comparison in this domain, as well as identify the strengths and weaknesses when dealing with environmental complexity.

This paper considers the task of matching images and sentences by learning a visual-textual embedding space for cross-modal retrieval. Finding such a space is a challenging task since the features and representations of text and image are not comparable. In this work, we introduce an end-to-end deep multimodal convolutional-recurrent network for learning both vision and language representations simultaneously to infer image-text similarity. The model learns which pairs are a match (positive) and which ones are a mismatch (negative) using a hinge-based triplet ranking. To learn about the joint representations, we leverage our newly extracted collection of tweets from Twitter. The main characteristic of our dataset is that the images and tweets are not standardized the same as the benchmarks. Furthermore, there can be a higher semantic correlation between the pictures and tweets contrary to benchmarks in which the descriptions are well-organized. Experimental results on MS-COCO benchmark dataset show that our model outperforms certain methods presented previously and has competitive performance compared to the state-of-the-art. The code and dataset have been made available publicly.

Deep reinforcement learning is successful in decision making for sophisticated games, such as Atari, Go, etc. However, real-world decision making often requires reasoning with partial information extracted from complex visual observations. This paper presents Discriminative Particle Filter Reinforcement Learning (DPFRL), a new reinforcement learning framework for complex partial observations. DPFRL encodes a differentiable particle filter in the neural network policy for explicit reasoning with partial observations over time. The particle filter maintains a belief using learned discriminative update, which is trained end-to-end for decision making. We show that using the discriminative update instead of standard generative models results in significantly improved performance, especially for tasks with complex visual observations, because they circumvent the difficulty of modeling complex observations that are irrelevant to decision making. In addition, to extract features from the particle belief, we propose a new type of belief feature based on the moment generating function. DPFRL outperforms state-of-the-art POMDP RL models in Flickering Atari Games, an existing POMDP RL benchmark, and in Natural Flickering Atari Games, a new, more challenging POMDP RL benchmark introduced in this paper. Further, DPFRL performs well for visual navigation with real-world data in the Habitat environment.

Deep Learning: Deep Learning is a subset of device machine learning and artificial intelligence with a few algorithms referred by the shape and feature of the brain known as artificial neural networks. Deep Learning may be supervised, semi-supervised or unsupervised. Machine Learning: Machine learning is a Subset of artificial intelligence (AI) that allow systems the ability to automatically learn and improve from previous event without being leaving programmed. Set of instruction build a mathematical model based on sample data, known as "training data". Artificial Neural Networks: Artificial neural networks (ANN) also known as as connectionist structures are computing structures slightly referred through the biological neural networks that are present in human brains.

The cellular industry's shift from long-distance radio signals to short-distance millimeter waves is one of the 5G era's biggest changes, expected to continue with submillimeter waves over the next decade. To more precisely direct millimeter wave and future terahertz-frequency signals toward user devices, Arizona State University researchers have developed ViWi-BT, a vision-wireless framework that improves beam tracking using computer vision and deep learning. Smartphones historically operated much like other long-distance radios, scanning the airwaves for omnidirectional tower signals and tuning into whatever was strongest and/or closest. But in the 5G and 6G eras, networks of small cells will use beamforming antennas to more specifically target their signals in a given direction toward discovered client devices, which may be contemplating connections from multiple base stations at once. ViWi-BT's goal is to use AI and a device's cameras or lidar capabilities to identify physical impediments and advantages for the beam targeting process, enabling "vision-aided wireless communications."

While much of the literature and buzz on deep learning concerns computer vision and natural language processing(NLP), audio analysis -- a field that includes automatic speech recognition(ASR), digital signal processing, and music classification, tagging, and generation -- is a growing subdomain of deep learning applications. Some of the most popular and widespread machine learning systems, virtual assistants Alexa, Siri, and Google Home, are largely products built atop models that can extract information from audio signals. Audio data analysis is about analyzing and understanding audio signals captured by digital devices, with numerous applications in the enterprise, healthcare, productivity, and smart cities. Applications include customer satisfaction analysis from customer support calls, media content analysis and retrieval, medical diagnostic aids and patient monitoring, assistive technologies for people with hearing impairments, and audio analysis for public safety. In the first part of this article series, we will talk about all you need to know before getting started with the audio data analysis and extract necessary features from a sound/audio file. We will also build an Artificial Neural Network(ANN) for the music genre classification.

Precisely defining artificial intelligence is tricky. John McCarthy proposed that AI is the simulation of human intelligence by machines for the inaugural summer research project in 1956. Others have defined AI as the study of intelligent agents, human or not, that can perceive their environments and take actions to maximize their chances of achieving some goal. Jerry Kaplan wrestles with the question for an entire chapter in his book Artificial Intelligence: What Everyone Needs To Know before giving up on a succinct definition. Rather than try to define AI precisely, we'll simply differentiate AI's goals and techniques: Some people use Artificial Intelligence and Machine Learning interchangeably.