#NeuralNetworks: Feedforward and #Backpropagation Explained & Optimization
What is neural networks? Developers should understand backpropagation, to figure out why their code sometimes does not work. Visual and down to earth explanation of the math of backpropagation.
Link
🔭 @DeepGravity
What is neural networks? Developers should understand backpropagation, to figure out why their code sometimes does not work. Visual and down to earth explanation of the math of backpropagation.
Link
🔭 @DeepGravity
Machine Learning From Scratch
Neural Networks: Feedforward and Backpropagation Explained
What is neural networks? Developers should understand backpropagation, to figure out why their code sometimes does not work. Visual and down to earth explanation of the math of backpropagation.
Semantic Segmentation of Thigh Muscle using 2.5D #DeepLearning Network Trained with Limited Datasets
Purpose: We propose a 2.5D #deep learning #NeuralNetwork (#DLNN) to automatically classify thigh muscle into 11 classes and evaluate its classification accuracy over 2D and 3D DLNN when trained with limited datasets. Enables operator invariant quantitative assessment of the thigh muscle volume change with respect to the disease progression. Materials and methods: Retrospective datasets consist of 48 thigh volume (TV) cropped from CT DICOM images. Cropped volumes were aligned with femur axis and resample in 2 mm voxel-spacing. Proposed 2.5D DLNN consists of three 2D U-Net trained with axial, coronal and sagittal muscle slices respectively. A voting algorithm was used to combine the output of U-Nets to create final segmentation. 2.5D U-Net was trained on PC with 38 TV and the remaining 10 TV were used to evaluate segmentation accuracy of 10 classes within Thigh. The result segmentation of both left and right thigh were de-cropped to original CT volume space. Finally, segmentation accuracies were compared between proposed DLNN and 2D/3D U-Net. Results: Average segmentation DSC score accuracy of all classes with 2.5D U-Net as 91.18 mean DSC score for 2D U-Net was 3.3 DSC score of 3D U-Net was 5.7 same datasets. Conclusion: We achieved a faster computationally efficient and automatic segmentation of thigh muscle into 11 classes with reasonable accuracy. Enables quantitative evaluation of muscle atrophy with disease progression.
Link
🔭 @DeepGravity
Purpose: We propose a 2.5D #deep learning #NeuralNetwork (#DLNN) to automatically classify thigh muscle into 11 classes and evaluate its classification accuracy over 2D and 3D DLNN when trained with limited datasets. Enables operator invariant quantitative assessment of the thigh muscle volume change with respect to the disease progression. Materials and methods: Retrospective datasets consist of 48 thigh volume (TV) cropped from CT DICOM images. Cropped volumes were aligned with femur axis and resample in 2 mm voxel-spacing. Proposed 2.5D DLNN consists of three 2D U-Net trained with axial, coronal and sagittal muscle slices respectively. A voting algorithm was used to combine the output of U-Nets to create final segmentation. 2.5D U-Net was trained on PC with 38 TV and the remaining 10 TV were used to evaluate segmentation accuracy of 10 classes within Thigh. The result segmentation of both left and right thigh were de-cropped to original CT volume space. Finally, segmentation accuracies were compared between proposed DLNN and 2D/3D U-Net. Results: Average segmentation DSC score accuracy of all classes with 2.5D U-Net as 91.18 mean DSC score for 2D U-Net was 3.3 DSC score of 3D U-Net was 5.7 same datasets. Conclusion: We achieved a faster computationally efficient and automatic segmentation of thigh muscle into 11 classes with reasonable accuracy. Enables quantitative evaluation of muscle atrophy with disease progression.
Link
🔭 @DeepGravity
#Classification-driven Single Image Dehazing
Most existing dehazing algorithms often use hand-crafted features or #ConvolutionalNeuralNetworks (#CNN)-based methods to generate clear images using pixel-level Mean Square Error (MSE) loss. The generated images generally have better visual appeal, but not always have better performance for high-level vision tasks, e.g. image classification. In this paper, we investigate a new point of view in addressing this problem. Instead of focusing only on achieving good quantitative performance on pixel-based metrics such as Peak Signal to Noise Ratio (PSNR), we also ensure that the dehazed image itself does not degrade the performance of the high-level vision tasks such as image classification. To this end, we present an unified CNN architecture that includes three parts: a dehazing sub-network (DNet), a classification-driven Conditional #GenerativeAdversarialNetworks sub-network (CCGAN) and a classification sub-network (CNet) related to image classification, which has better performance both on visual appeal and image classification. We conduct comprehensive experiments on two challenging benchmark datasets for fine-grained and object classification: CUB-200-2011 and Caltech-256. Experimental results demonstrate that the proposed method outperforms many recent state-of-the-art single image dehazing methods in terms of image dehazing metrics and classification accuracy.
Link
🔭 @DeepGravity
Most existing dehazing algorithms often use hand-crafted features or #ConvolutionalNeuralNetworks (#CNN)-based methods to generate clear images using pixel-level Mean Square Error (MSE) loss. The generated images generally have better visual appeal, but not always have better performance for high-level vision tasks, e.g. image classification. In this paper, we investigate a new point of view in addressing this problem. Instead of focusing only on achieving good quantitative performance on pixel-based metrics such as Peak Signal to Noise Ratio (PSNR), we also ensure that the dehazed image itself does not degrade the performance of the high-level vision tasks such as image classification. To this end, we present an unified CNN architecture that includes three parts: a dehazing sub-network (DNet), a classification-driven Conditional #GenerativeAdversarialNetworks sub-network (CCGAN) and a classification sub-network (CNet) related to image classification, which has better performance both on visual appeal and image classification. We conduct comprehensive experiments on two challenging benchmark datasets for fine-grained and object classification: CUB-200-2011 and Caltech-256. Experimental results demonstrate that the proposed method outperforms many recent state-of-the-art single image dehazing methods in terms of image dehazing metrics and classification accuracy.
Link
🔭 @DeepGravity
A nice and simple introduction to #MachineLearning
Machine Learning is undeniably one of the most influential and powerful technologies in today’s world. More importantly, we are far from seeing its full potential. There’s no doubt, it will continue to be making headlines for the foreseeable future. This article is designed as an introduction to the Machine Learning concepts, covering all the fundamental ideas without being too high level.
Link
🔭 @DeepGravity
Machine Learning is undeniably one of the most influential and powerful technologies in today’s world. More importantly, we are far from seeing its full potential. There’s no doubt, it will continue to be making headlines for the foreseeable future. This article is designed as an introduction to the Machine Learning concepts, covering all the fundamental ideas without being too high level.
Link
🔭 @DeepGravity
Medium
Machine Learning | An Introduction
An introduction to Machine Learning and its 4 approaches
How to Perform #ObjectDetection With #YOLOv3 in #Keras
After completing this tutorial, you will know:
* YOLO-based #ConvolutionalNeuralNetwork family of models for object detection and the most recent variation called YOLOv3.
* The best-of-breed open source library implementation of the YOLOv3 for the Keras deep learning library.
* How to use a pre-trained YOLOv3 to perform object localization and detection on new photographs.
Link
🔭 @DeepGravity
After completing this tutorial, you will know:
* YOLO-based #ConvolutionalNeuralNetwork family of models for object detection and the most recent variation called YOLOv3.
* The best-of-breed open source library implementation of the YOLOv3 for the Keras deep learning library.
* How to use a pre-trained YOLOv3 to perform object localization and detection on new photographs.
Link
🔭 @DeepGravity
Iteratively-Refined Interactive 3D Medical Image Segmentation with Multi-Agent #ReinforcementLearning
Existing automatic 3D image segmentation methods usually fail to meet the clinic use. Many studies have explored an interactive strategy to improve the image segmentation performance by iteratively incorporating user hints. However, the dynamic process for successive interactions is largely ignored. We here propose to model the dynamic process of iterative interactive image segmentation as a #MarkovDecisionProcess (#MDP) and solve it with reinforcement learning (#RL). Unfortunately, it is intractable to use single-agent RL for voxel-wise prediction due to the large exploration space. To reduce the exploration space to a tractable size, we treat each voxel as an agent with a shared voxel-level behavior strategy so that it can be solved with multi-agent reinforcement learning. An additional advantage of this multi-agent model is to capture the dependency among voxels for segmentation task. Meanwhile, to enrich the information of previous segmentations, we reserve the prediction uncertainty in the state space of MDP and derive an adjustment action space leading to a more precise and finer segmentation. In addition, to improve the efficiency of exploration, we design a relative cross-entropy gain-based reward to update the policy in a constrained direction. Experimental results on various medical datasets have shown that our method significantly outperforms existing state-of-the-art methods, with the advantage of fewer interactions and a faster convergence.
Link
🔭 @DeepGravity
Existing automatic 3D image segmentation methods usually fail to meet the clinic use. Many studies have explored an interactive strategy to improve the image segmentation performance by iteratively incorporating user hints. However, the dynamic process for successive interactions is largely ignored. We here propose to model the dynamic process of iterative interactive image segmentation as a #MarkovDecisionProcess (#MDP) and solve it with reinforcement learning (#RL). Unfortunately, it is intractable to use single-agent RL for voxel-wise prediction due to the large exploration space. To reduce the exploration space to a tractable size, we treat each voxel as an agent with a shared voxel-level behavior strategy so that it can be solved with multi-agent reinforcement learning. An additional advantage of this multi-agent model is to capture the dependency among voxels for segmentation task. Meanwhile, to enrich the information of previous segmentations, we reserve the prediction uncertainty in the state space of MDP and derive an adjustment action space leading to a more precise and finer segmentation. In addition, to improve the efficiency of exploration, we design a relative cross-entropy gain-based reward to update the policy in a constrained direction. Experimental results on various medical datasets have shown that our method significantly outperforms existing state-of-the-art methods, with the advantage of fewer interactions and a faster convergence.
Link
🔭 @DeepGravity
Merging Deterministic #PolicyGradient Estimations with Varied #Bias - #Variance Tradeoff for Effective #DeepReinforcementLearning
Deep reinforcement learning (#DRL) on #MarkovDecisionProcess (#MDPs) with continuous action spaces is often approached by directly updating parametric policies along the direction of estimated policy gradients (PGs). Previous research revealed that the performance of these PG algorithms depends heavily on the bias-variance tradeoff involved in estimating and using PGs. A notable approach towards balancing this tradeoff is to merge both on-policy and off-policy gradient estimations for the purpose of training stochastic policies. However this method cannot be utilized directly by sample-efficient off-policy PG algorithms such as #DeepDeterministicPolicyGradient (#DDPG) and #twindelayedDDPG ( #TD3), which have been designed to train deterministic policies. It is hence important to develop new techniques to merge multiple off-policy estimations of deterministic PG (DPG). Driven by this research question, this paper introduces elite #DPG which will be estimated differently from conventional DPG to emphasize on the variance reduction effect at the expense of increased learning bias. To mitigate the extra bias, policy consolidation techniques will be developed to distill policy behavioral knowledge from elite trajectories and use the distilled generative model to further regularize policy training. Moreover, we will study both theoretically and experimentally two different DPG merging methods, i.e., interpolation merging and two-step merging, with the aim to induce varied bias-variance tradeoff through combined use of both conventional DPG and elite DPG. Experiments on six benchmark control tasks confirm that these two merging methods can noticeably improve the learning performance of TD3, significantly outperforming several state-of-the-art #DRL algorithms.
Link
🔭 @DeepGravity
Deep reinforcement learning (#DRL) on #MarkovDecisionProcess (#MDPs) with continuous action spaces is often approached by directly updating parametric policies along the direction of estimated policy gradients (PGs). Previous research revealed that the performance of these PG algorithms depends heavily on the bias-variance tradeoff involved in estimating and using PGs. A notable approach towards balancing this tradeoff is to merge both on-policy and off-policy gradient estimations for the purpose of training stochastic policies. However this method cannot be utilized directly by sample-efficient off-policy PG algorithms such as #DeepDeterministicPolicyGradient (#DDPG) and #twindelayedDDPG ( #TD3), which have been designed to train deterministic policies. It is hence important to develop new techniques to merge multiple off-policy estimations of deterministic PG (DPG). Driven by this research question, this paper introduces elite #DPG which will be estimated differently from conventional DPG to emphasize on the variance reduction effect at the expense of increased learning bias. To mitigate the extra bias, policy consolidation techniques will be developed to distill policy behavioral knowledge from elite trajectories and use the distilled generative model to further regularize policy training. Moreover, we will study both theoretically and experimentally two different DPG merging methods, i.e., interpolation merging and two-step merging, with the aim to induce varied bias-variance tradeoff through combined use of both conventional DPG and elite DPG. Experiments on six benchmark control tasks confirm that these two merging methods can noticeably improve the learning performance of TD3, significantly outperforming several state-of-the-art #DRL algorithms.
Link
🔭 @DeepGravity
An official #PyTorch implementation of “Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation” (#NeurIPS 2019) by Risto Vuorio*, Shao-Hua Sun*, Hexiang Hu, and Joseph J. Lim
This project is an implementation of Multimodal Model-Agnostic #MetaLearning via Task-Aware Modulation, which is published in NeurIPS 2019. Please contact Shao-Hua Sun for any questions.
Model-agnostic meta-learners aim to acquire meta-prior parameters from a distribution of tasks and adapt to novel tasks with few gradient updates. Yet, seeking a common initialization shared across the entire task distribution substantially limits the diversity of the task distributions that they are able to learn from. We propose a multimodal MAML (MMAML) framework, which is able to modulate its meta-learned prior according to the identified mode, allowing more efficient fast adaptation. An illustration of the proposed framework is as follows.
Link
🔭 @DeepGravity
This project is an implementation of Multimodal Model-Agnostic #MetaLearning via Task-Aware Modulation, which is published in NeurIPS 2019. Please contact Shao-Hua Sun for any questions.
Model-agnostic meta-learners aim to acquire meta-prior parameters from a distribution of tasks and adapt to novel tasks with few gradient updates. Yet, seeking a common initialization shared across the entire task distribution substantially limits the diversity of the task distributions that they are able to learn from. We propose a multimodal MAML (MMAML) framework, which is able to modulate its meta-learned prior according to the identified mode, allowing more efficient fast adaptation. An illustration of the proposed framework is as follows.
Link
🔭 @DeepGravity
GitHub
shaohua0116/MMAML-Classification
An official PyTorch implementation of “Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation” (NeurIPS 2019) by Risto Vuorio*, Shao-Hua Sun*, Hexiang Hu, and Joseph J. Lim - shaohua0116...
#Text2FaceGAN: Face Generation from Fine Grained Textual Denoscriptions
Powerful #GenerativeAdversarialNetworks ( 3GAN) have been developed to automatically synthesize realistic images from text. However, most existing tasks are limited to generating simple images such as flowers from captions. In this work, we extend this problem to the less addressed domain of face generation from fine-grained textual denoscriptions of face, e.g., "A person has curly hair, oval face, and mustache". We are motivated by the potential of automated face generation to impact and assist critical tasks such as criminal face reconstruction. Since current datasets for the task are either very small or do not contain captions, we generate captions for images in the CelebA dataset by creating an algorithm to automatically convert a list of attributes to a set of captions. We then model the highly multi-modal problem of text to face generation as learning the conditional distribution of faces (conditioned on text) in same latent space. We utilize the current state-of-the-art GAN (DC-GAN with GAN-CLS loss) for learning conditional multi-modality. The presence of more fine-grained details and variable length of the captions makes the problem easier for a user but more difficult to handle compared to the other text-to-image tasks. We flipped the labels for real and fake images and added noise in discriminator. Generated images for diverse textual denoscriptions show promising results. In the end, we show how the widely used inceptions score is not a good metric to evaluate the performance of generative models used for synthesizing faces from text.
Link
🔭 @DeepGravity
Powerful #GenerativeAdversarialNetworks ( 3GAN) have been developed to automatically synthesize realistic images from text. However, most existing tasks are limited to generating simple images such as flowers from captions. In this work, we extend this problem to the less addressed domain of face generation from fine-grained textual denoscriptions of face, e.g., "A person has curly hair, oval face, and mustache". We are motivated by the potential of automated face generation to impact and assist critical tasks such as criminal face reconstruction. Since current datasets for the task are either very small or do not contain captions, we generate captions for images in the CelebA dataset by creating an algorithm to automatically convert a list of attributes to a set of captions. We then model the highly multi-modal problem of text to face generation as learning the conditional distribution of faces (conditioned on text) in same latent space. We utilize the current state-of-the-art GAN (DC-GAN with GAN-CLS loss) for learning conditional multi-modality. The presence of more fine-grained details and variable length of the captions makes the problem easier for a user but more difficult to handle compared to the other text-to-image tasks. We flipped the labels for real and fake images and added noise in discriminator. Generated images for diverse textual denoscriptions show promising results. In the end, we show how the widely used inceptions score is not a good metric to evaluate the performance of generative models used for synthesizing faces from text.
Link
🔭 @DeepGravity
#DBSN: Measuring Uncertainty through #Bayesian Learning of #DeepNeuralNetwork Structures
Bayesian neural networks (BNNs) introduce uncertainty estimation to #deep networks by performing Bayesian inference on network weights. However, such models bring the challenges of inference, and further BNNs with weight uncertainty rarely achieve superior performance to standard models. In this paper, we investigate a new line of Bayesian deep learning by performing Bayesian reasoning on the structure of deep neural networks. Drawing inspiration from the neural architecture search, we define the network structure as gating weights on the redundant operations between computational nodes, and apply stochastic variational inference techniques to learn the structure distributions of networks. Empirically, the proposed method substantially surpasses the advanced deep neural networks across a range of classification and segmentation tasks. More importantly, our approach also preserves benefits of Bayesian principles, producing improved uncertainty estimation than the strong baselines including MC dropout and variational #BNNs algorithms (e.g. noisy EK-FAC).
Link
🔭 @DeepGravity
Bayesian neural networks (BNNs) introduce uncertainty estimation to #deep networks by performing Bayesian inference on network weights. However, such models bring the challenges of inference, and further BNNs with weight uncertainty rarely achieve superior performance to standard models. In this paper, we investigate a new line of Bayesian deep learning by performing Bayesian reasoning on the structure of deep neural networks. Drawing inspiration from the neural architecture search, we define the network structure as gating weights on the redundant operations between computational nodes, and apply stochastic variational inference techniques to learn the structure distributions of networks. Empirically, the proposed method substantially surpasses the advanced deep neural networks across a range of classification and segmentation tasks. More importantly, our approach also preserves benefits of Bayesian principles, producing improved uncertainty estimation than the strong baselines including MC dropout and variational #BNNs algorithms (e.g. noisy EK-FAC).
Link
🔭 @DeepGravity
Algorithmic Improvements for #DeepReinforcement #Learning applied to Interactive Fiction
Text-based games are a natural challenge domain for deep reinforcement learning algorithms. Their state and action spaces are combinatorially large, their reward function is sparse, and they are partially observable: the agent is informed of the consequences of its actions through textual feedback. In this paper we emphasize this latter point and consider the design of a deep reinforcement learning agent that can play from feedback alone. Our design recognizes and takes advantage of the structural characteristics of text-based games. We first propose a contextualisation mechanism, based on accumulated reward, which simplifies the learning problem and mitigates partial observability. We then study different methods that rely on the notion that most actions are ineffectual in any given situation, following Zahavy et al.'s idea of an admissible action. We evaluate these techniques in a series of text-based games of increasing difficulty based on the TextWorld framework, as well as the iconic game Zork. Empirically, we find that these techniques improve the performance of a baseline deep reinforcement learning agent applied to text-based games.
Link
🔭 @DeepGravity
Text-based games are a natural challenge domain for deep reinforcement learning algorithms. Their state and action spaces are combinatorially large, their reward function is sparse, and they are partially observable: the agent is informed of the consequences of its actions through textual feedback. In this paper we emphasize this latter point and consider the design of a deep reinforcement learning agent that can play from feedback alone. Our design recognizes and takes advantage of the structural characteristics of text-based games. We first propose a contextualisation mechanism, based on accumulated reward, which simplifies the learning problem and mitigates partial observability. We then study different methods that rely on the notion that most actions are ineffectual in any given situation, following Zahavy et al.'s idea of an admissible action. We evaluate these techniques in a series of text-based games of increasing difficulty based on the TextWorld framework, as well as the iconic game Zork. Empirically, we find that these techniques improve the performance of a baseline deep reinforcement learning agent applied to text-based games.
Link
🔭 @DeepGravity
#Google Introduces New Metrics for #AI -Generated Audio and Video Quality
Google AI researchers published two new metrics for measuring the quality of audio and video generated by deep-learning networks, the Fréchet Audio Distance (FAD) and Fréchet Video Distance (FVD). The metrics have been shown to have a high correlation with human evaluations of quality.
Link
🔭 @DeepGravity
Google AI researchers published two new metrics for measuring the quality of audio and video generated by deep-learning networks, the Fréchet Audio Distance (FAD) and Fréchet Video Distance (FVD). The metrics have been shown to have a high correlation with human evaluations of quality.
Link
🔭 @DeepGravity
InfoQ
Google Introduces New Metrics for AI-Generated Audio and Video Quality
Google AI researchers published two new metrics for measuring the quality of audio and video generated by deep-learning networks, the Fréchet Audio Distance (FAD) and Fréchet Video Distance (FVD). The metrics have been shown to have a high correlation with…
Introducing TensorBoard.dev: a new way to share your #ML experiment results
TensorBoard, TensorFlow’s visualization toolkit, is often used by researchers and engineers to visualize and understand their ML experiments. It enables tracking experiment metrics, visualizing models, profiling ML programs, visualizing hyperparameter tuning experiments, and much more.
#TensorBoard
Link
🔭 @DeepGravity
TensorBoard, TensorFlow’s visualization toolkit, is often used by researchers and engineers to visualize and understand their ML experiments. It enables tracking experiment metrics, visualizing models, profiling ML programs, visualizing hyperparameter tuning experiments, and much more.
#TensorBoard
Link
🔭 @DeepGravity
blog.tensorflow.org
Introducing TensorBoard.dev: a new way to share your ML experiment results
The TensorFlow blog contains regular news from the TensorFlow team and the community, with articles on Python, TensorFlow.js, TF Lite, TFX, and more.