Developments in Artificial Intelligence (AI) and Distributed Ledger Technology (DLT) currently lead lively debates in academia and practice. AI processes data to perform tasks that were previously thought possible only for humans to perform. DLT acts in uncertain environments to create consensus over data among a group of participants. In recent articles, both technologies complement each other. Examples include the design of secure distributed ledgers or the creation of allied learning systems distributed across multiple nodes. This can lead to technological convergence, which in the past, has paved the way for major IT product innovations. Previous work highlights several potential benefits of the convergence of AI and DLT but only provides a limited theoretical framework to describe upcoming real-world integration cases of both technologies. We aim to contribute by conducting a systematic literature review on the previous work and by providing rigorously derived future research opportunities. Our analysis identifies how AI and DLT exchange data, and how to use these integration principles to build new systems. Based on that, we present open questions for future research. This work helps researchers active in AI or DLT to overcome current limitations in their field, and engineers to develop systems along with the convergence of these technologies.

A great number of computer vision publications have focused on distinguishing between human action recognition and classification rather than the intensity of actions performed. Indexing the intensity which determines the performance of human actions is a challenging task due to the uncertainty and information deficiency that exists in the video inputs. To remedy this uncertainty, in this paper, we coupled fuzzy logic rules with the neural-based action recognition model to index the intensity of the action as intense or mild. In our approach, we define fuzzy logic rules to detect the intensity index of the performed action using the weights generated by the Spatio-Temporal LSTM and demonstrate through experiments that indexing of the action intensity is possible. We analyzed the integrated model by applying it to videos of human actions with different action intensities and were able to achieve an accuracy of 89.16% on our generated dataset for intensity indexing. The integrated model demonstrates the ability of the fuzzy inference module to effectively estimate the intensity index of the human action.

Recent research developing neural network architectures with external memory have often used the benchmark bAbI question and answering dataset which provides a challenging number of tasks requiring reasoning. Here we employed a classic associative inference task from the memory-based reasoning neuroscience literature in order to more carefully probe the reasoning capacity of existing memory-augmented architectures. This task is thought to capture the essence of reasoning -- the appreciation of distant relationships among elements distributed across multiple facts or memories. Surprisingly, we found that current architectures struggle to reason over long distance associations. Similar results were obtained on a more complex task involving finding the shortest path between nodes in a path. We therefore developed MEMO, an architecture endowed with the capacity to reason over longer distances. This was accomplished with the addition of two novel components. First, it introduces a separation between memories (facts) stored in external memory and the items that comprise these facts in external memory. Second, it makes use of an adaptive retrieval mechanism, allowing a variable number of "memory hops" before the answer is produced. MEMO is capable of solving our novel reasoning tasks, as well as match state of the art results in bAbI.

In recent years, there has been an increasing interest in studying causality-related properties in machine learning models generally, and in generative models in particular. While that is well motivated, it inherits the fundamental computational hardness of probabilistic inference, making exact reasoning intractable. Probabilistic tractable models have also recently emerged, which guarantee that conditional marginals can be computed in time linear in the size of the model, where the model is usually learned from data. Although initially limited to low tree-width models, recent tractable models such as sum product networks (SPNs) and probabilistic sentential decision diagrams (PSDDs) exploit efficient function representations and also capture high tree-width models. In this paper, we ask the following technical question: can we use the distributions represented or learned by these models to perform causal queries, such as reasoning about interventions and counterfactuals? By appealing to some existing ideas on transforming such models to Bayesian networks, we answer mostly in the negative. We show that when transforming SPNs to a causal graph interventional reasoning reduces to computing marginal distributions; in other words, only trivial causal reasoning is possible. For PSDDs the situation is only slightly better. We first provide an algorithm for constructing a causal graph from a PSDD, which introduces augmented variables. Intervening on the original variables, once again, reduces to marginal distributions, but when intervening on the augmented variables, a deterministic but nonetheless causal-semantics can be provided for PSDDs.

Recurrent neural networks (RNNs) are a powerful approach for time series prediction. However, their performance is strongly affected by their architecture and hyperparameter settings. The architecture optimization of RNNs is a time-consuming task, where the search space is typically a mixture of real, integer and categorical values. To allow for shrinking and expanding the size of the network, the representation of architectures often has a variable length. In this paper, we propose to tackle the architecture optimization problem with a variant of the Bayesian Optimization (BO) algorithm. To reduce the evaluation time of candidate architectures the Mean Absolute Error Random Sampling (MRS), a training-free method to estimate the network performance, is adopted as the objective function for BO. Also, we propose three fixed-length encoding schemes to cope with the variable-length architecture representation. The result is a new perspective on accurate and efficient design of RNNs, that we validate on three problems. Our findings show that 1) the BO algorithm can explore different network architectures using the proposed encoding schemes and successfully designs well-performing architectures, and 2) the optimization time is significantly reduced by using MRS, without compromising the performance as compared to the architectures obtained from the actual training procedure.

This helps users experience a hassle-free environment and enhances rendition. The solution includes human pose estimation using Tensor flow and OpenCV frameworks. Unlike most yoga applications that use traditional programming, Deep learning along with computer vision are used to generate the model where the back end is powered by AI and the front end is done using google framework flutter. The concept is simple yet effective as it is cost-efficient and very simple to use where minimum hardware specifications such as ram of 1 GB and a camera of 16mp along with basic storage will suffice, It can be used by everyone as due to user-friendly UI and inbuilt voice assistant will provide users the necessary instructions for the next posture. The camera heeds the user's posture and automatically suggests exercise.

The goal of the variational autoencoder (VAE) is to learn a probability distribution $Pr(\mathbf{x})$ over a multi-dimensional variable $\mathbf{x}$. There are two main reasons for modelling distributions. First, we might want to draw samples (generate) from the distribution to create new plausible values of $\mathbf{x}$. Second, we might want to measure the likelihood that a new vector $\mathbf{x} {*}$ was created by this probability distribution. In fact, it turns out that the variational autoencoder is well-suited to the former task but not for the latter. It is common to talk about the variational autoencoder as if it is the model of $Pr(\mathbf{x})$. However, this is misleading; the variational autoencoder is a neural architecture that is designed to help learn the model for $Pr(\mathbf{x})$.

Navigating a new indoor space without any prior knowledge or even a map is a challenging task for a human, let alone a robot. To help develop intelligent machines that interact more effectively with complex 3D environments, Facebook researchers developed a GPU-accelerated deep reinforcement learning model that achieves near 100 percent success in navigating a variety of virtual environments without a pre-provided map. To achieve this breakthrough, the team focused their work on developing an efficient approach to scaling RL models, which require a significant number of training samples, using multi-node distribution. "A single parameter server and thousands of (typically CPU) workers may be fundamentally incompatible with the needs of modern computer vision and robotics communities," the researchers explained in their post, Near-perfect point-goal navigation from 2.5 billion frames of experience. "Unlike Gym or Atari, 3D simulators require GPU acceleration…. The desired agents operate from high-dimensional inputs (pixels) and use deep networks, such as ResNet50, which strain the parameter server. Thus, existing distributed RL architectures do not scale and there is a need to develop a new distributed architecture."

In recent years, researchers have been developing increasingly advanced computational techniques, such as deep learning algorithms, to complete a variety of tasks. One task that they have been trying to address is known as "sketch-based image retrieval" (SBIR). SBIR tasks entail retrieving images of a particular object or visual concept among a wide collection or database based on sketches made by human users. To automate this task, researchers have been trying to develop tools that can analyze human sketches and identify images that are related to the sketch or contain the same object. Despite the promising results achieved by some of these tools, developing techniques that perform consistently well on SBIR tasks has so far proved challenging.