Want to be notified of new releases in Tianxiaomo/pytorch-YOLOv4?

The report "Artificial Intelligence in Agriculture Market by Technology (Machine Learning, Computer Vision, and Predictive Analytics), Offering (Software, Hardware, AI-as-a-Service, and Services), Application, and Geography - Global Forecast to 2026", is estimated to be USD 1.0 billion in 2020 and is projected to reach USD 4.0 billion by 2026, at a CAGR of 25.5% between 2020 and 2026. The market growth is driven by the increasing implementation of data generation through sensors and aerial images for crops, increasing crop productivity through deep-learning technology, and government support for the adoption of modern agricultural techniques. Browse 81 market data Tables and 40 Figures spread through 152 Pages and in-depth TOC on "Artificial Intelligence in Agriculture Market by Technology (Machine Learning, Computer Vision, and Predictive Analytics), Offering (Software, Hardware, AI-as-a-Service, and Services), Application, and Geography - Global Forecast to 2026" The market for drone analytics is expected to grow at the highest rate due to its extensive use for diagnosing and mapping to evaluate crop health and to make real-time decisions. Favorable government mandates for the use of drones in agriculture are also expected to fuel the growth of the drone analytics market. Increasing awareness among farm owners regarding the advantages associated with AI technology is expected to further fuel the growth of the AI in agriculture market.

Are you interested in AI, machine learning and deep learning? Do not miss this free video.

Ore deposits are generally formed by hydrothermal activity, which also forms various types of alteration zones in the vicinity of such deposits. Identifying alteration zones can clarify the mineralization mechanism and provides information indispensable for mineral resource exploration. The application of an alteration halo accompanied by the alteration of host rocks to the exploration of the Kuroko ore deposits produced many results in Japan (see, e.g., [1]). It is important to identify the alteration zone in the exploration of porphyry copper deposits. More than 50% of global copper production is from porphyry copper deposits, making them the most important copper resource.

A team of Uber AI researchers has developed a set of algorithms, Go-Explore, that reportedly beats any Atari 2600 game with "superhuman" scores, including ones where AI previously had trouble besting its organic rivals. The key is a system that takes care to remember promising states and returns to those states before it sets out exploring. Go-Explore saw improvement by "orders of magnitude" in some games. It was the first to beat every level in Montezuma's Revenge, and got a "near-perfect" Pitfall score -- both of these are particularly challenging for reinforcement learning systems like this. DeepMind's Agent57 reached a similar benchmark, according to the team's Jeff Clune, but through "entirely different methods."

A recent source of concern for the security of neural networks is the emergence of clean-label dataset poisoning attacks, wherein correctly labeled poisoned samples are injected in the training dataset. While these poisons look legitimate to the human observer, they contain malicious characteristics that trigger a targeted misclassification during inference. We propose a scalable and transferable clean-label attack, Bullseye Polytope, which creates poison images centered around the target image in the feature space. Bullseye Polytope improves the attack success rate of the current state-of-the-art by 26.75% in end-to-end training, while increasing attack speed by a factor of 12. We further extend Bullseye Polytope to a more practical attack model by including multiple images of the same object (e.g., from different angles) in crafting the poisoned samples. We demonstrate that this extension improves attack transferability by over 16% to unseen images (of the same object) without increasing the number of poisons.

Recently, a race towards the simplification of deep networks has begun, showing that it is effectively possible to reduce the size of these models with minimal or no performance loss. However, there is a general lack in understanding why these pruning strategies are effective. In this work, we are going to compare and analyze pruned solutions with two different pruning approaches, one-shot and gradual, showing the higher effectiveness of the latter. In particular, we find that gradual pruning allows access to narrow, well-generalizing minima, which are typically ignored when using one-shot approaches. In this work we also propose PSP-entropy, a measure to understand how a given neuron correlates to some specific learned classes. Interestingly, we observe that the features extracted by iteratively-pruned models are less correlated to specific classes, potentially making these models a better fit in transfer learning approaches.

A large number of deep learning architectures use spatial transformations of CNN feature maps or filters to better deal with variability in object appearance caused by natural image transformations. In this paper, we prove that spatial transformations of CNN feature maps cannot align the feature maps of a transformed image to match those of its original, for general affine transformations, unless the extracted features are themselves invariant. Our proof is based on elementary analysis for both the single-and multi-layer network case. The results imply that methods based on spatial transformations of CNN feature maps or filters cannot replace image alignment of the input and cannot enable invariant recognition for general affine transformations, specifically not for scaling transformations or shear transformations. For rotations and reflections, spatially transforming feature maps or filters can enable invariance but only for networks with learnt or hardcoded rotation-or reflection-invariant features.

Automatic transistor sizing is a challenging problem in circuit design due to the large design space, complex performance trade-offs, and fast technological advancements. Although there has been plenty of work on transistor sizing targeting on one circuit, limited research has been done on transferring the knowledge from one circuit to another to reduce the re-design overhead. In this paper, we present GCN-RL Circuit Designer, leveraging reinforcement learning (RL) to transfer the knowledge between different technology nodes and topologies. Moreover, inspired by the simple fact that circuit is a graph, we learn on the circuit topology representation with graph convolutional neural networks (GCN). The GCN-RL agent extracts features of the topology graph whose vertices are transistors, edges are wires. Our learning-based optimization consistently achieves the highest Figures of Merit (FoM) on four different circuits compared with conventional black-box optimization methods (Bayesian Optimization, Evolutionary Algorithms), random search, and human expert designs. Experiments on transfer learning between five technology nodes and two circuit topologies demonstrate that RL with transfer learning can achieve much higher FoMs than methods without knowledge transfer. Our transferable optimization method makes transistor sizing and design porting more effective and efficient.

We describe our submission to the Extreme Value Analysis 2019 Data Challenge in which teams were asked to predict extremes of sea surface temperature anomaly within spatio-temporal regions of missing data. We present a computational framework which reconstructs missing data using convolutional deep neural networks. Conditioned on incomplete data, we employ autoencoder-like models as multivariate conditional distributions from which possible reconstructions of the complete dataset are sampled using imputed noise. In order to mitigate bias introduced by any one particular model, a prediction ensemble is constructed to create the final distribution of extremal values. Our method does not rely on expert knowledge in order to accurately reproduce dynamic features of a complex oceanographic system with minimal assumptions. The obtained results promise reusability and generalization to other domains.