After developing an AI system that can beat Go and chess, Google-owned DeepMind started tackling a different class of games: multiplayer ones, which usually require teamwork. In a paper published by Science, a group of DeepMind researchers have detailed how they designed an AI system that was able to master capture the flag mode in Quake III. The system uses "AI agents" to represent its players in the game, which can play with or against human opponents. DeepMind trained those agents with 450,000 rounds of capture the flag, which total four years of gameplay completed over the span of a few weeks. The AI agents started out doing random movements, but after playing again and again and again, they eventually figured out the strategies and techniques that work.

Enterprises have been using analytical machine learning techniques for years to solve business problems related to making predictions on raw data. Today, perception-based techniques driven by deep learning and neural networks are gaining traction around understanding vision and language, both of which have applications within enterprise settings. When people speak of enterprise artificial intelligence (AI), it is quite common to treat it as a generic term or one large entity without being specific about what technology is being used. This can lead to misunderstandings around what AI can and cannot do, the software and hardware that is required, or even the talent needed to develop the AI solution. However, these techniques should be treated separately from the deep learning branch of AI.

Are the robots really taking over? By robots, I mean artificially intelligent machine-based learning algorithms that mimic the workings of a human brain. With all the buzz about Artificial intelligence (AI) and machine learning now you would think that the human brain and the way we think, act, make decisions, and operate in the world is on the way out. In fact, the way the current technology operates – using neural networks – is somewhat incongruent to the workings of the human brain. "I don't think it's how the brain works. We clearly don't need all the labeled data."

Are the robots really taking over? By robots, I mean artificially intelligent machine-based learning algorithms that mimic the workings of a human brain. With all the buzz about Artificial intelligence (AI) and machine learning now you would think that the human brain and the way we think, act, make decisions, and operate in the world is on the way out. In fact, the way the current technology operates – using neural networks – is somewhat incongruent to the workings of the human brain. "I don't think it's how the brain works. We clearly don't need all the labeled data."

It's been roughly a year since I posted my viral "AI winter is well on its way" post and like I promised I'll periodically post an update on the general AI landscape. I posted one some 6 months ago and now is time for another one. And there has been a lot of stuff going on lately and none of it has changed my mind - the AI bubble is bursting. And as with every bubble bursting we are in a blowoff phase in which those who have the most to lose are pulling out the most outrageous confidence pumping pieces they could think of, the ultimate strategy to con some more naive people to give them money. But let's go over what has been going on.

Artificial intelligence can already beat humans at video games like StarCraft II and Dota 2, but now they've also mastered the art of working cooperatively. DeepMind has trained AIs to team up to play Quake III Arena, a first-person shooter video game. They can outperform human players and are also able to successfully work with human teammates. Up until now, AI has not been able to master the complexity of games that require teamwork and interaction between multiple players. A group of 30 AIs were collectively trained to play five-minute rounds of Capture the Flag, a game mode in which teams must retrieve flags from their opponents while retaining their own.

In this research work, probabilistic decision-making approaches are studied, e.g. Bayesian and Boltzmann strategies, along with various deterministic exploration strategies, e.g. greedy, epsilon-Greedy and random approaches. In this research work, a comparative study has been done between probabilistic and deterministic decision-making approaches, the experiments are performed in OpenAI gym environment, solving Cart Pole problem. This research work discusses about the Bayesian approach to decision-making in deep reinforcement learning, and about dropout, how it can reduce the computational cost. All the exploration approaches are compared. It also discusses about the importance of exploration in deep reinforcement learning, and how improving exploration strategies may help in science and technology. This research work shows how probabilistic decision-making approaches are better in the long run as compared to the deterministic approaches. When there is uncertainty, Bayesian dropout approach proved to be better than all other approaches in this research work.

In this paper, we develop a convolutional neural network model to predict the mechanical properties of a two-dimensional checkerboard composite quantitatively. The checkerboard composite possesses two phases, one phase is soft and ductile while the other is stiff and brittle. The ground-truth data used in the training process are obtained from finite element analyses under the assumption of plane stress. Monte Carlo simulations and central limit theorem are used to find the size of the dataset needed. Once the training process is completed, the developed model is validated using data unseen during training. The developed neural network model captures the stiffness, strength, and toughness of checkerboard composites with high accuracy. Also, we integrate the developed model with a genetic algorithm (GA) optimizer to identify the optimal microstructural designs. The genetic algorithm optimizer adopted here has several operators, selection, crossover, mutation, and elitism. The optimizer converges to configurations with highly enhanced properties. For the case of the modulus and starting from randomly-initialized generation, the GA optimizer converges to the global maximum which involves no soft elements. Also, the GA optimizers, when used to maximize strength and toughness, tend towards having soft elements in the region next to the crack tip.

Recommender systems have become ubiquitous, transforming user interactions with products, services and content in a wide variety of domains. In content recommendation, recommenders generally surface relevant and/or novel personalized content based on learned models of user preferences (e.g., as in collaborative filtering [Breese et al., 1998, Konstan et al., 1997, Srebro et al., 2004, Salakhutdinov and Mnih, 2007]) or predictive models of user responses to specific recommendations. Well-known applications of recommender systems include video recommendations on YouTube [Covington et al., 2016], movie recommendations on Netflix [Gomez-Uribe and Hunt, 2016] and playlist construction on Spotify [Jacobson et al., 2016]. It is increasingly common to train deep neural networks (DNNs) [van den Oord et al., 2013, Wang et al., 2015, Covington et al., 2016, Cheng et al., 2016] to predict user responses (e.g., click-through rates, content engagement, ratings, likes) to generate, score and serve candidate recommendations. Practical recommender systems largely focus on myopic prediction--estimating a user's immediate response to a recommendation--without considering the long-term impact on subsequent user behavior. This can be limiting: modeling a recommendation's stochastic impact on the future affords opportunities to trade off user engagement in the near-term for longer-term benefit (e.g., by probing a user's interests, or improving satisfaction).

Real-world applications often combine learning and optimization problems on graphs. For instance, our objective may be to cluster the graph in order to detect meaningful communities (or solve other common graph optimization problems such as facility location, maxcut, and so on). However, graphs or related attributes are often only partially observed, introducing learning problems such as link prediction which must be solved prior to optimization. We propose an approach to integrate a differentiable proxy for common graph optimization problems into training of machine learning models for tasks such as link prediction. This allows the model to focus specifically on the downstream task that its predictions will be used for. Experimental results show that our end-to-end system obtains better performance on example optimization tasks than can be obtained by combining state of the art link prediction methods with expert-designed graph optimization algorithms.