Artificial intelligence (AI)-generated marketing campaign company Persado has unveiled a new product, along with a fresh $30 million credit facility to fuel further expansion, reports Julie Muhn at Finovate (Banking Technology's sister company). Persado One, the new offering, provides personalised emotional engagement at scale. The company says the new development represents the "most significant advancement to date" of Persado's AI platform. Available through the company's enterprise level of service, Persado One uses deep learning algorithms to deliver personalised messaging to a customer based on their emotional profile. The company is also launching a professional class of tools to help marketers predict response rates, generate higher performing campaigns, and refine language according to a brand's style.

We analyze the expressiveness and loss surface of practical deep convolutional neural networks (CNNs) with shared weights and max pooling layers. We show that such CNNs produce linearly independent features at a "wide" layer which has more neurons than the number of training samples. This condition holds e.g. for the VGG network. Furthermore, we provide for such wide CNNs necessary and sufficient conditions for global minima with zero training error. For the case where the wide layer is followed by a fully connected layer we show that almost every critical point of the empirical loss is a global minimum with zero training error. Our analysis suggests that both depth and width are very important in deep learning. While depth brings more representational power and allows the network to learn high level features, width smoothes the optimization landscape of the loss function in the sense that a sufficiently wide network has a well-behaved loss surface with potentially no bad local minima. It is well known that the optimization problem for training neural networks can have exponentially many local minima (Auer et al., 1996; Safran & Shamir, 2016) and NPhardness has been shown in many cases (Blum & Rivest., 1989; Sima, 2002; Livni et al., 2014; Shamir, 2017; Shalev-Shwartz et al., 2017). However, it has been empirically observed (Dauphin et al., 2014; Goodfellow et al., 2015) that the training of state-of-the-art deep CNNs (LeCun et al., 1990; Krizhevsky et al., 2012), which are often overparameterized, is not hampered by suboptimal local minima. However, it turns out that these approaches are either not practical as they require e.g. For deep linear networks one has achieved a quite complete picture of the loss surface as it has been shown that every local minimum is a global minimum (Baldi & Hornik, 1988; Kawaguchi, 2016; Freeman & Bruna, 2017; Hardt & Ma, 2017; Y un et al., 2017). By randomizing the nonlinear part of a feedforward network with ReLU activation function and making some additional simplifying assumptions, Choromanska et al. (2015a) can relate the loss surface of neural networks to a certain spin glass model. In this model the objective of local minima is close to the global optimum and the number of bad local minima decreases quickly with the distance to the global optimum. This is a very interesting result but is based on a number of unrealistic assumptions (Choromanska et al., 2015b). More recently, Nguyen & Hein (2017) have analyzed deep fully connected networks with general activation functions and could show that almost every critical point is a global minimum if one layer has more neurons than the number of training points. While this result holds for networks in practice, it requires a quite extensively overparameterized network. 1 This paper is one of the first ones, which studies deep CNNs.

A model for hit song prediction can be used in the pop music industry to identify emerging trends and potential artists or songs before they are marketed to the public. While most previous work formulates hit song prediction as a regression or classification problem, we present in this paper a convolutional neural network (CNN) model that treats it as a ranking problem. Specifically, we use a commercial dataset with daily play-counts to train a multi-objective Siamese CNN model with Euclidean loss and pairwise ranking loss to learn from audio the relative ranking relations among songs. Besides, we devise a number of pair sampling methods according to some empirical observation of the data. Our experiment shows that the proposed model with a sampling method called A/B sampling leads to much higher accuracy in hit song prediction than the baseline regression model. Moreover, we can further improve the accuracy by using a neural attention mechanism to extract the highlights of songs and by using a separate CNN model to offer high-level features of songs.

Why and how that deep learning works well on different tasks remains a mystery from a theoretical perspective. In this paper we draw a geometric picture of the deep learning system by finding its analogies with two existing geometric structures, the geometry of quantum computations and the geometry of the diffeomorphic template matching. In this framework, we give the geometric structures of different deep learning systems including convolutional neural networks, residual networks, recursive neural networks, recurrent neural networks and the equilibrium prapagation framework. We can also analysis the relationship between the geometrical structures and their performance of different networks in an algorithmic level so that the geometric framework may guide the design of the structures and algorithms of deep learning systems.

Deep learning models require extensive architecture design exploration and hyperparameter optimization to perform well on a given task. The exploration of the model design space is often made by a human expert, and optimized using a combination of grid search and search heuristics over a large space of possible choices. Neural Architecture Search (NAS) is a Reinforcement Learning approach that has been proposed to automate architecture design. NAS has been successfully applied to generate Neural Networks that rival the best human-designed architectures. However, NAS requires sampling, constructing, and training hundreds to thousands of models to achieve well-performing architectures. This procedure needs to be executed from scratch for each new task. The application of NAS to a wide set of tasks currently lacks a way to transfer generalizable knowledge across tasks. In this paper, we present the Multitask Neural Model Search (MNMS) controller. Our goal is to learn a generalizable framework that can condition model construction on successful model searches for previously seen tasks, thus significantly speeding up the search for new tasks. We demonstrate that MNMS can conduct an automated architecture search for multiple tasks simultaneously while still learning well-performing, specialized models for each task. We then show that pre-trained MNMS controllers can transfer learning to new tasks. By leveraging knowledge from previous searches, we find that pre-trained MNMS models start from a better location in the search space and reduce search time on unseen tasks, while still discovering models that outperform published human-designed models.

We propose a new statistical model suitable for machine learning of systems with long distance correlations such as natural languages. The model is based on directed acyclic graph decorated by multi-linear tensor maps in the vertices and vector spaces in the edges, called tensor network. Such tensor networks have been previously employed for effective numerical computation of the renormalization group flow on the space of effective quantum field theories and lattice models of statistical mechanics. We provide explicit algebro-geometric analysis of the parameter moduli space for tree graphs, discuss model properties and applications such as statistical translation.

Development systems for deep learning, such as Theano, Torch, TensorFlow, or MXNet, are easy-to-use tools for creating complex neural network models. Since gradient computations are automatically baked in, and execution is mapped to high performance hardware, these models can be trained end-to-end on large amounts of data. However, it is currently not easy to implement many basic machine learning primitives in these systems (such as Gaussian processes, least squares estimation, principal components analysis, Kalman smoothing), mainly because they lack efficient support of linear algebra primitives as differentiable operators. We detail how a number of matrix decompositions (Cholesky, LQ, symmetric eigen) can be implemented as differentiable operators. We have implemented these primitives in MXNet, running on CPU and GPU in single and double precision. We sketch use cases of these new operators, learning Gaussian process and Bayesian linear regression models. Our implementation is based on BLAS/LAPACK APIs, for which highly tuned implementations are available on all major CPUs and GPUs.

This paper takes a step towards temporal reasoning in a dynamically changing video, not in the pixel space that constitutes its frames, but in a latent space that describes the non-linear dynamics of the objects in its world. We introduce the Kalman variational auto-encoder, a framework for unsupervised learning of sequential data that disentangles two latent representations: an object's representation, coming from a recognition model, and a latent state describing its dynamics. As a result, the evolution of the world can be imagined and missing data imputed, both without the need to generate high dimensional frames at each time step. The model is trained end-to-end on videos of a variety of simulated physical systems, and outperforms competing methods in generative and missing data imputation tasks.

We provide an overview of several non-linear activation functions in a neural network architecture that have proven successful in many machine learning applications. We conduct an empirical analysis on the effectiveness of using these function on the MNIST classification task, with the aim of clarifying which functions produce the best results overall. Based on this first set of results, we examine the effects of building deeper architectures with an increasing number of hidden layers. We also survey the impact of using, on the same task, different initialisation schemes for the weights of our neural network. Using these sets of experiments as a base, we conclude by providing a optimal neural network architecture that yields impressive results in accuracy on the MNIST classification task.

Inspired by the success of deep learning techniques in the physical and chemical sciences, we apply a modification of an autoencoder type deep neural network to the task of dimension reduction of molecular dynamics data. We can show that our time-lagged autoencoder reliably finds low-dimensional embeddings for highdimensional feature spaces which capture the slow dynamics of the underlying stochastic processes-beyond the capabilities of linear dimension reduction techniques. Molecular dynamics (MD) simulation allows us to probe the full spatiotemporal detail of molecular processes, but its usefulness has long been limited by the sampling problem. If we do not want to choose the library of feature functions by hand, but instead want to optimize the nonlinear mapping E by employing a neural network, we have again two options: (1) employ the variational approach. In this paper we investigate option (2), which naturally leads to using a time-lagged autoencoder (TAE).