When we talk about data science or artificial intelligence, the two very common terminologies that come into account are MACHINE LEARNING and DEEP LEARNING. But it is substantially seen that both the terms are faultily used interchangeably. So let us find out what is the difference between the two and how both the terms are interrelated with each other. The term machine learning refers to a technology which enables a device to perform a task without any human intervention. In other words, machine learning is that field of data science which consists of the algorithms that perform the learning procedure without human assistance.

What's new: AlphaGo's initial iteration was trained on a database of human Go games whereas the newer AlphaGo Zero's artificial neural networks use the current state of the game as input. Through trial and error and feedback in the form of winning, the AI learned how to play. It then used that same network to choose its next move whereas AlphaGo used a separate network. This reinforcement learning strategy, which was used extensively by AlphaGo as well, has its roots in psychology: the neural network learns from rewards like humans do. The DeepMind researchers wrote: "the self-learned player performed much better overall, defeating the human-trained player within the first 24h of training. This suggests that AlphaGo Zero may be learning a strategy that is qualitatively different to human play."

Posted by Bradley Jiang, Software Engineer. Many people think designing deep learning models and training neural networks is complex and time-consuming, taking days or even weeks of work. But it doesn't have to be. There are a number of tools you can use right now to help you quickly develop and iterate on machine learning models. One such tool is Cloud Datalab.

Join us on the 26th of October for presentations about some of the technologies and workshops you'll find at the BuzzConf Technology Festival this year. This month is packed with presentations on Arduinos, Insertable Technology, Voice Assistants, Deep Learning & Maker Culture. Tickets are also now on sale for the festival in December, but if you haven't yet got a ticket and want to see what all the buzz is about first - this is a great session to come down to! You can also see videos from many of our events on YouTube. Held in The Loop Bar in Melbourne, there will be plenty of options to eat and drink late into the night!

I have a pretty awesome backlog of blog posts from Udacity Self-Driving Car students, partly because they're doing awesome things and partly because I fell behind on reviewing them for a bit. Here are five that look pretty neat. This is a great blog post if you're looking to get started with point cloud files. The most popular laptop among Silicon Valley software developers is the Macbook Pro. The current version of the Macbook Pro, however, does not include an NVIDIA GPU, which restricts its ability to use CUDA and cuDNN, NVIDIA's tools for accelerating deep learning.

Docking is an important tool in computational drug discovery that aims to predict the binding pose of a ligand to a target protein through a combination of pose scoring and optimization. A scoring function that is differentiable with respect to atom positions can be used for both scoring and gradient-based optimization of poses for docking. Using a differentiable grid-based atomic representation as input, we demonstrate that a scoring function learned by training a convolutional neural network (CNN) to identify binding poses can also be applied to pose optimization. We also show that an iteratively-trained CNN that includes poses optimized by the first CNN in its training set performs even better at optimizing randomly initialized poses than either the first CNN scoring function or AutoDock Vina.

We identify a strong equivalence between neural network based machine learning (ML) methods and the formulation of statistical data assimilation (DA), known to be a problem in statistical physics. DA, as used widely in physical and biological sciences, systematically transfers information in observations to a model of the processes producing the observations. The correspondence is that layer label in the ML setting is the analog of time in the data assimilation setting. Utilizing aspects of this equivalence we discuss how to establish the global minimum of the cost functions in the ML context, using a variational annealing method from DA. This provides a design method for optimal networks for ML applications and may serve as the basis for understanding the success of "deep learning." Results from an ML example are presented. When the layer label is taken to be continuous, the Euler-Lagrange equation for the ML optimization problem is an ordinary differential equation, and we see that the problem being solved is a two point boundary value problem. The use of continuous layers is denoted "deepest learning". The Hamiltonian version provides a direct rationale for back propagation as a solution method for the canonical momentum; however, it suggests other solution methods are to be preferred.

Deep learning typically requires training a very capable architecture using large datasets. However, many important learning problems demand an ability to draw valid inferences from small size datasets, and such problems pose a particular challenge for deep learning. In this regard, various researches on "meta-learning" are being actively conducted. Recent work has suggested a Memory Augmented Neural Network (MANN) for meta-learning. MANN is an implementation of a Neural Turing Machine (NTM) with the ability to rapidly assimilate new data in its memory, and use this data to make accurate predictions. In models such as MANN, the input data samples and their appropriate labels from previous step are bound together in the same memory locations. This often leads to memory interference when performing a task as these models have to retrieve a feature of an input from a certain memory location and read only the label information bound to that location. In this paper, we tried to address this issue by presenting a more robust MANN. We revisited the idea of meta-learning and proposed a new memory augmented neural network by explicitly splitting the external memory into feature and label memories. The feature memory is used to store the features of input data samples and the label memory stores their labels. Hence, when predicting the label of a given input, our model uses its feature memory unit as a reference to extract the stored feature of the input, and based on that feature, it retrieves the label information of the input from the label memory unit. In order for the network to function in this framework, a new memory-writingmodule to encode label information into the label memory in accordance with the meta-learning task structure is designed. Here, we demonstrate that our model outperforms MANN by a large margin in supervised one-shot classification tasks using Omniglot and MNIST datasets.

Time series forecasting is widely used in a multitude of domains. In this paper, we present four models to predict the stock price using the S&P 500 index as input time series data. The mean (martingale) and ordinary linear models require the strongest assumption in stationarity which we use as baseline models. The generalized linear model (GLM) requires lesser assumptions but is unable to outperform the martingale. In empirical testing, the RNN model performs the best comparing to other two models, because it will update the input through LSTM instantaneously, but also does not beat the martingale. In addition, we introduce an online-to-batch (OTB) algorithm and discrepancy measure to inform readers the state-of-art predicting method, which doesn't require any stationarity or non-mixing assumptions in time series data. Finally, to apply these forecasting to practice, we introduce basic trading strategies that can create Win-win and Zero-sum situations.

A new form of the variational autoencoder (VAE) is proposed, based on the symmetric Kullback-Leibler divergence. It is demonstrated that learning of the resulting symmetric VAE (sVAE) has close connections to previously developed adversarial-learning methods. This relationship helps unify the previously distinct techniques of VAE and adversarially learning, and provides insights that allow us to ameliorate shortcomings with some previously developed adversarial methods. In addition to an analysis that motivates and explains the sVAE, an extensive set of experiments validate the utility of the approach.