Search Results for author:
Found 38 papers, 20 papers with code
Beyond The Rainbow: High Performance Deep Reinforcement Learning On A Desktop PC
Rainbow Deep Q-Network (DQN) demonstrated combining multiple independent enhancements could significantly boost a reinforcement learning (RL) agent's performance.
Rethinking Deep Thinking: Stable Learning of Algorithms using Lipschitz Constraints
Iterative algorithms solve problems by taking steps until a solution is reached.
Fluid Dynamic DNNs for Reliable and Adaptive Distributed Inference on Edge Devices
Distributed inference is a popular approach for efficient DNN inference at the edge.
Dynamic DNNs and Runtime Management for Efficient Inference on Mobile/Embedded Devices
In this thesis, we proposed a combined method, a system was developed for DNN performance trade-off management, combining the runtime trade-off opportunities in both algorithms and hardware to meet dynamically changing application performance targets and hardware constraints in real time.
Improving the Robustness of Neural Multiplication Units with Reversible Stochasticity
Multilayer Perceptrons struggle to learn certain simple arithmetic tasks.
Physically Embodied Deep Image Optimisation
Physical sketches are created by learning programs to control a drawing robot.
Shared Visual Representations of Drawing for Communication: How do different biases affect human interpretability and intent?
We present an investigation into how representational losses can affect the drawings produced by artificial agents playing a communication game.
Learning Division with Neural Arithmetic Logic Modules
To achieve systematic generalisation, it first makes sense to master simple tasks such as arithmetic.
Orthogonalising gradients to speedup neural network optimisation
The optimisation of neural networks can be sped up by orthogonalising the gradients before the optimisation step, ensuring the diversification of the learned representations.
GhostShiftAddNet: More Features from Energy-Efficient Operations
When compared to GhostNet, inference latency on the Jetson Nano is improved by 1. 3x and 2x on the GPU and CPU respectively.
What Remains of Visual Semantic Embeddings
Although different paradigms of visual semantic embedding models are designed to align visual features and distributed word representations, it is unclear to what extent current ZSL models encode semantic information from distributed word representations.
Language Models as Zero-shot Visual Semantic Learners
We find that contextual representations in language mod-els outperform static word embeddings, when the compositional chain of object is short.
Dynamic Transformer for Efficient Machine Translation on Embedded Devices
The new reduced design space results in a BLEU score increase of approximately 1% for sub-optimal models from the original design space, with a wide range for performance scaling between 0. 356s - 1. 526s for the GPU and 2. 9s - 7. 31s for the CPU.
Temporal Early Exits for Efficient Video Object Detection
In this paper, we propose temporal early exits to reduce the computational complexity of per-frame video object detection.
Learning to Draw: Emergent Communication through Sketching
Evidence that visual communication preceded written language and provided a basis for it goes back to prehistory, in forms such as cave and rock paintings depicting traces of our distant ancestors.
Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms
However, the training process of such dynamic DNNs can be costly, since platform-aware models of different deployment scenarios must be retrained to become dynamic.
Differentiable Drawing and Sketching
We present a bottom-up differentiable relaxation of the process of drawing points, lines and curves into a pixel raster.
The emergence of visual semantics through communication games
The majority of work has focused on using fixed, pretrained image feature extraction networks which potentially bias the information the agents learn to communicate.
A Primer for Neural Arithmetic Logic Modules
Neural Arithmetic Logic Modules have become a growing area of interest, though remain a niche field.
Anatomically Constrained ResNets Exhibit Opponent Receptive Fields; So What?
Primate visual systems are well known to exhibit varying degrees of bottlenecks in the early visual pathway.
How Convolutional Neural Network Architecture Biases Learned Opponency and Colour Tuning
The colour tuning data can further be used to form a rich understanding of how colour is encoded by a network.
Linear Disentangled Representations and Unsupervised Action Estimation
In this work we empirically show that linear disentangled representations are not generally present in standard VAE models and that they instead require altering the loss landscape to induce them.
FMix: Enhancing Mixed Sample Data Augmentation
Finally, we show that a consequence of the difference between interpolating MSDA such as MixUp and masking MSDA such as FMix is that the two can be combined to improve performance even further.
Ranked #3 on
Image Classification
on Fashion-MNIST
Avoiding hashing and encouraging visual semantics in referential emergent language games
There has been an increasing interest in the area of emergent communication between agents which learn to play referential signalling games with realistic images.
Spatial and Colour Opponency in Anatomically Constrained Deep Networks
Colour vision has long fascinated scientists, who have sought to understand both the physiology of the mechanics of colour vision and the psychophysics of colour perception.
Imagining the Latent Space of a Variational Auto-Encoders
Variational Auto-Encoders (VAEs) are designed to capture compressible information about a dataset.
Deep Set Prediction Networks
Current approaches for predicting sets from feature vectors ignore the unordered nature of sets and suffer from discontinuity issues as a result.
FSPool: Learning Set Representations with Featurewise Sort Pooling
Traditional set prediction models can struggle with simple datasets due to an issue we call the responsibility problem.
Probabilistic Semantic Embedding
We present an extension of a variational auto-encoder that creates semantically richcoupled probabilistic latent representations that capture the semantics of multiplemodalities of data.
A Biologically Inspired Visual Working Memory for Deep Networks
The state of our Hebb-Rosenblatt memory is embedded in STAWM as the weights space of a layer.
Learning Representations of Sets through Optimized Permutations
Representations of sets are challenging to learn because operations on sets should be permutation-invariant.
Torchbearer: A Model Fitting Library for PyTorch
We introduce torchbearer, a model fitting library for pytorch aimed at researchers working on deep learning or differentiable programming.
Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata
While Wikipedia exists in 287 languages, its content is unevenly distributed among them.
Learning to Count Objects in Natural Images for Visual Question Answering
Visual Question Answering (VQA) models have struggled with counting objects in natural images so far.
Ranked #32 on
Visual Question Answering (VQA)
on VQA v2 test-std
Neural Wikipedian: Generating Textual Summaries from Knowledge Base Triples
We explore the problem of generating natural language summaries for Semantic Web data.
A Neural Network Approach for Knowledge-Driven Response Generation
Our model is based on a Recurrent Neural Network (RNN) that is trained over concatenated sequences of comments, a Convolution Neural Network that is trained over Wikipedia sentences and a formulation that couples the two trained embeddings in a multimodal space.
