Research papers and code for "Misha Denil":
In this paper we demonstrate that two common problems in Machine Learning---imbalanced and overlapping data distributions---do not have independent effects on the performance of SVM classifiers. This result is notable since it shows that a model of either of these factors must account for the presence of the other. Our study of the relationship between these problems has lead to the discovery of a previously unreported form of "covert" overfitting which is resilient to commonly used empirical regularization techniques. We demonstrate the existance of this covert phenomenon through several methods based around the parametric regularization of trained SVMs. Our findings in this area suggest a possible approach to quantifying overlap in real world data sets.

Click to Read Paper and Get Code
It has recently been observed that certain extremely simple feature encoding techniques are able to achieve state of the art performance on several standard image classification benchmarks including deep belief networks, convolutional nets, factored RBMs, mcRBMs, convolutional RBMs, sparse autoencoders and several others. Moreover, these "triangle" or "soft threshold" encodings are ex- tremely efficient to compute. Several intuitive arguments have been put forward to explain this remarkable performance, yet no mathematical justification has been offered. The main result of this report is to show that these features are realized as an approximate solution to the a non-negative sparse coding problem. Using this connection we describe several variants of the soft threshold features and demonstrate their effectiveness on two image classification benchmark tasks.

Click to Read Paper and Get Code
We present a hierarchical convolutional document model with an architecture designed to support introspection of the document structure. Using this model, we show how to use visualisation techniques from the computer vision literature to identify and extract topic-relevant sentences. We also introduce a new scalable evaluation technique for automatic sentence extraction systems that avoids the need for time consuming human annotation of validation data.

* arXiv admin note: substantial text overlap with arXiv:1406.3830
Click to Read Paper and Get Code
Despite widespread interest and practical use, the theoretical properties of random forests are still not well understood. In this paper we contribute to this understanding in two ways. We present a new theoretically tractable variant of random regression forests and prove that our algorithm is consistent. We also provide an empirical evaluation, comparing our algorithm and other theoretically tractable random forest models to the random forest algorithm used in practice. Our experiments provide insight into the relative importance of different simplifications that theoreticians have made to obtain tractable models for analysis.

* Under review by the International Conference on Machine Learning (ICML) 2014
Click to Read Paper and Get Code
As a testament to their success, the theory of random forests has long been outpaced by their application in practice. In this paper, we take a step towards narrowing this gap by providing a consistency result for online random forests.

* To appear in Proceedings of the 30th International Conference on Machine Learning, 2013
Click to Read Paper and Get Code
Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of the activation function, which may hide dependencies that are not visible to vanilla-SGD (using first order gradients only). Gating mechanisms that use softly saturating activation functions to emulate the discrete switching of digital logic circuits are good examples of this. We propose to exploit the injection of appropriate noise so that the gradients may flow easily, even if the noiseless application of the activation function would yield zero gradient. Large noise will dominate the noise-free gradient and allow stochastic gradient descent toexplore more. By adding noise only to the problematic parts of the activation function, we allow the optimization procedure to explore the boundary between the degenerate (saturating) and the well-behaved parts of the activation function. We also establish connections to simulated annealing, when the amount of noise is annealed down, making it easier to optimize hard objective functions. We find experimentally that replacing such saturating activation functions by noisy variants helps training in many contexts, yielding state-of-the-art or competitive results on different datasets and task, especially when training seems to be the most difficult, e.g., when curriculum learning is necessary to obtain good results.

Click to Read Paper and Get Code
This paper presents foundational theoretical results on distributed parameter estimation for undirected probabilistic graphical models. It introduces a general condition on composite likelihood decompositions of these models which guarantees the global consistency of distributed estimators, provided the local estimators are consistent.

Click to Read Paper and Get Code
We introduce a new embarrassingly parallel parameter learning algorithm for Markov random fields with untied parameters which is efficient for a large class of practical models. Our algorithm parallelizes naturally over cliques and, for graphs of bounded degree, its complexity is linear in the number of cliques. Unlike its competitors, our algorithm is fully parallel and for log-linear models it is also data efficient, requiring only the local sufficient statistics of the data to estimate parameters.

Click to Read Paper and Get Code
The linear layer is one of the most pervasive modules in deep learning representations. However, it requires $O(N^2)$ parameters and $O(N^2)$ operations. These costs can be prohibitive in mobile applications or prevent scaling in many domains. Here, we introduce a deep, differentiable, fully-connected neural network module composed of diagonal matrices of parameters, $\mathbf{A}$ and $\mathbf{D}$, and the discrete cosine transform $\mathbf{C}$. The core module, structured as $\mathbf{ACDC^{-1}}$, has $O(N)$ parameters and incurs $O(N log N )$ operations. We present theoretical results showing how deep cascades of ACDC layers approximate linear layers. ACDC is, however, a stand-alone module and can be used in combination with any other types of module. In our experiments, we show that it can indeed be successfully interleaved with ReLU modules in convolutional neural networks for image recognition. Our experiments also study critical factors in the training of these structured modules, including initialization and depth. Finally, this paper also provides a connection between structured linear transforms used in deep learning and the field of Fourier optics, illustrating how ACDC could in principle be implemented with lenses and diffractive elements.

Click to Read Paper and Get Code
We present a new approach for transferring knowledge from groups to individuals that comprise them. We evaluate our method in text, by inferring the ratings of individual sentences using full-review ratings. This approach, which combines ideas from transfer learning, deep learning and multi-instance learning, reduces the need for laborious human labelling of fine-grained data when abundant labels are available at the group level.

Click to Read Paper and Get Code
We discuss an attentional model for simultaneous object tracking and recognition that is driven by gaze data. Motivated by theories of perception, the model consists of two interacting pathways: identity and control, intended to mirror the what and where pathways in neuroscience models. The identity pathway models object appearance and performs classification using deep (factored)-Restricted Boltzmann Machines. At each point in time the observations consist of foveated images, with decaying resolution toward the periphery of the gaze. The control pathway models the location, orientation, scale and speed of the attended object. The posterior distribution of these states is estimated with particle filtering. Deeper in the control pathway, we encounter an attentional mechanism that learns to select gazes so as to minimize tracking uncertainty. Unlike in our previous work, we introduce gaze selection strategies which operate in the presence of partial information and on a continuous action space. We show that a straightforward extension of the existing approach to the partial information setting results in poor performance, and we propose an alternative method based on modeling the reward surface as a Gaussian Process. This approach gives good performance in the presence of partial information and allows us to expand the action space from a small, discrete set of fixation points to a continuous domain.

Click to Read Paper and Get Code
We demonstrate that there is significant redundancy in the parameterization of several deep learning models. Given only a few weight values for each feature it is possible to accurately predict the remaining values. Moreover, we show that not only can the parameter values be predicted, but many of them need not be learned at all. We train several different architectures by learning only a small number of weights and predicting the rest. In the best case we are able to predict more than 95% of the weights of a network without any drop in accuracy.

Click to Read Paper and Get Code
Capturing the compositional process which maps the meaning of words to that of documents is a central challenge for researchers in Natural Language Processing and Information Retrieval. We introduce a model that is able to represent the meaning of documents by embedding them in a low dimensional vector space, while preserving distinctions of word and sentence order crucial for capturing nuanced semantics. Our model is based on an extended Dynamic Convolution Neural Network, which learns convolution filters at both the sentence and document level, hierarchically learning to capture and compose low level lexical features into high level semantic concepts. We demonstrate the effectiveness of this model on a range of document modelling tasks, achieving strong results with no feature engineering and with a more compact model. Inspired by recent advances in visualising deep convolution networks for computer vision, we present a novel visualisation technique for our document networks which not only provides insight into their learning process, but also can be interpreted to produce a compelling automatic summarisation system for texts.

Click to Read Paper and Get Code
We build deep RL agents that execute declarative programs expressed in formal language. The agents learn to ground the terms in this language in their environment, and can generalize their behavior at test time to execute new programs that refer to objects that were not referenced during training. The agents develop disentangled interpretable representations that allow them to generalize to a wide variety of zero-shot semantic tasks.

Click to Read Paper and Get Code
When encountering novel objects, humans are able to infer a wide range of physical properties such as mass, friction and deformability by interacting with them in a goal driven way. This process of active interaction is in the same spirit as a scientist performing experiments to discover hidden facts. Recent advances in artificial intelligence have yielded machines that can achieve superhuman performance in Go, Atari, natural language processing, and complex control problems; however, it is not clear that these systems can rival the scientific intuition of even a young child. In this work we introduce a basic set of tasks that require agents to estimate properties such as mass and cohesion of objects in an interactive simulated environment where they can manipulate the objects and observe the consequences. We found that state of art deep reinforcement learning methods can learn to perform the experiments necessary to discover such hidden properties. By systematically manipulating the problem difficulty and the cost incurred by the agent for performing experiments, we found that agents learn different strategies that balance the cost of gathering information against the cost of making mistakes in different situations.

Click to Read Paper and Get Code
This paper introduces the Intentional Unintentional (IU) agent. This agent endows the deep deterministic policy gradients (DDPG) agent for continuous control with the ability to solve several tasks simultaneously. Learning to solve many tasks simultaneously has been a long-standing, core goal of artificial intelligence, inspired by infant development and motivated by the desire to build flexible robot manipulators capable of many diverse behaviours. We show that the IU agent not only learns to solve many tasks simultaneously but it also learns faster than agents that target a single task at-a-time. In some cases, where the single task DDPG method completely fails, the IU agent successfully solves the task. To demonstrate this, we build a playroom environment using the MuJoCo physics engine, and introduce a grounded formal language to automatically generate tasks.

Click to Read Paper and Get Code
The fully connected layers of a deep convolutional neural network typically contain over 90% of the network parameters, and consume the majority of the memory required to store the network parameters. Reducing the number of parameters while preserving essentially the same predictive performance is critically important for operating deep neural networks in memory constrained environments such as GPUs or embedded devices. In this paper we show how kernel methods, in particular a single Fastfood layer, can be used to replace all fully connected layers in a deep convolutional neural network. This novel Fastfood layer is also end-to-end trainable in conjunction with convolutional layers, allowing us to combine them into a new architecture, named deep fried convolutional networks, which substantially reduces the memory footprint of convolutional networks trained on MNIST and ImageNet with no drop in predictive performance.

* svd experiments included
Click to Read Paper and Get Code
Learning to learn has emerged as an important direction for achieving artificial intelligence. Two of the primary barriers to its adoption are an inability to scale to larger problems and a limited ability to generalize to new tasks. We introduce a learned gradient descent optimizer that generalizes well to new tasks, and which has significantly reduced memory and computation overhead. We achieve this by introducing a novel hierarchical RNN architecture, with minimal per-parameter overhead, augmented with additional architectural features that mirror the known structure of optimization tasks. We also develop a meta-training ensemble of small, diverse optimization tasks capturing common properties of loss landscapes. The optimizer learns to outperform RMSProp/ADAM on problems in this corpus. More importantly, it performs comparably or better when applied to small convolutional neural networks, despite seeing no neural networks in its meta-training set. Finally, it generalizes to train Inception V3 and ResNet V2 architectures on the ImageNet dataset for thousands of steps, optimization problems that are of a vastly different scale than those it was trained on. We release an open source implementation of the meta-training algorithm.

* Final ICML paper after reviewer suggestions
Click to Read Paper and Get Code
We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent. We show that these learned optimizers exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad range of derivative-free black-box functions, including Gaussian process bandits, simple control objectives, global optimization benchmarks and hyper-parameter tuning tasks. Up to the training horizon, the learned optimizers learn to trade-off exploration and exploitation, and compare favourably with heavily engineered Bayesian optimization packages for hyper-parameter tuning.

* Accepted by ICML 2017. Previous version "Learning to Learn for Global Optimization of Black Box Functions" was published in the Deep Reinforcement Learning Workshop, NIPS 2016
Click to Read Paper and Get Code
The move from hand-designed features to learned features in machine learning has been wildly successful. In spite of this, optimization algorithms are still designed by hand. In this paper we show how the design of an optimization algorithm can be cast as a learning problem, allowing the algorithm to learn to exploit structure in the problems of interest in an automatic way. Our learned algorithms, implemented by LSTMs, outperform generic, hand-designed competitors on the tasks for which they are trained, and also generalize well to new tasks with similar structure. We demonstrate this on a number of tasks, including simple convex problems, training neural networks, and styling images with neural art.

Click to Read Paper and Get Code