Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

/pdf/deep-residual-learning-for-image-recognition-b75jg61qrq.pdf

Deep Residual Learning for Image Recognition

In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

Very Deep Convolutional Networks for Large-Scale Image Recognition

Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers---8x deeper than VGG nets but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. 
The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Deep Learning

Using porous materials as a carrier to adsorb and store CO2 in the vast underground mine goaf is a feasible and effective route to achieve “emission peak” and “carbon neutrality”, because this method boasts the advantages of a large storage capacity and remarkable safety. In this research, first, alkaline waste carbide slag was adopted to mineralize and store CO2. Afterward, a new type of environmentally friendly porous particles for efficiently adsorbing and storing CO2 in the mine goaf was prepared through the one-step synthesis method using mineralized carbide slag (CS) as the aggregate, oleic acid (OA) as the anionic surfactant, cetyl trimithyl ammonium bromide (CTAB) as the cationic surfactant and sodium hypochlorite (NaClO) as the foaming agent. According to the single-factor experiment results, the optimal ratio of porous particles with a high porosity and a large specific surface area was concluded, i.e., CS = 65–67.5 wt%, OA = 2.75–3.25 wt%, CTAB = 0.2–0.28 wt%, NaClO = 4.25–4.5 wt% and H2O = 40 wt%. Under this ratio, the particles enjoy excellent compressive strength and CO2 static adsorption capacity, i.e., 102.4–110.7 N and 213.7–321.4 cm3/g, respectively. By adding the amount of CO2 mineralized by alkaline waste (0.41 g/g) and the CO2 adsorption capacity of waste-based porous particles (321.4 cm³/g), it is calculated that one ton of solid waste can absorb about 1 tons of CO2. This research discloses the effects of various factors on the compressive strength and CO2 adsorption capacity of porous particles and provides important guidance for the development of high-performance porous CO2 adsorbents in the goaf. 

Synthesis of high-strength porous particles based on alkaline solid waste: a promising CO2-capturing material for mine goafs

. Semantic segmentation of LiDAR point clouds is an impor-tant task in autonomous driving. However, training deep models via con-ventional supervised methods requires large datasets which are costly to label. It is critical to have label-eﬃcient segmentation approaches to scale up the model to new operational domains or to improve performance on rare cases. While most prior works focus on indoor scenes, we are one of the ﬁrst to propose a label-eﬃcient semantic segmentation pipeline for outdoor scenes with LiDAR point clouds. Our method co-designs an eﬃcient labeling process with semi/weakly supervised learning and is applicable to nearly any 3D semantic segmentation backbones. Speciﬁ-cally, we leverage geometry patterns in outdoor scenes to have a heuristic pre-segmentation to reduce the manual labeling and jointly design the learning targets with the labeling process. In the learning step, we leverage prototype learning to get more descriptive point embeddings and use multi-scan distillation to exploit richer semantics from temporally aggregated point clouds to boost the performance of single-scan models. Evaluated on the SemanticKITTI and the nuScenes datasets, we show that our proposed method outperforms existing label-eﬃcient methods. With extremely limited human annotations ( e.g ., 0.1% point labels), our proposed method is even highly competitive compared to the fully supervised counterpart with 100% labels.

LESS: Label-Eﬃcient Semantic Segmentation for LiDAR Point Clouds

A significant challenge for the control of a robotic lower extremity rehabilitation exoskeleton is to ensure stability and robustness during programmed tasks or motions, which is crucial for the safety of the mobility-impaired user. Due to various levels of the user's disability, the human-exoskeleton interaction forces and external perturbations are unpredictable and could vary substantially and cause conventional motion controllers to behave unreliably or the robot to fall down. In this work, we propose a new, reinforcement learning-based, motion controller for a lower extremity rehabilitation exoskeleton, aiming to perform collaborative squatting exercises with efficiency, stability, and strong robustness. Unlike most existing rehabilitation exoskeletons, our exoskeleton has ankle actuation on both sagittal and front planes and is equipped with multiple foot force sensors to estimate center of pressure (CoP), an important indicator of system balance. This proposed motion controller takes advantage of the CoP information by incorporating it in the state input of the control policy network and adding it to the reward during the learning to maintain a well balanced system state during motions. In addition, we use dynamics randomization and adversary force perturbations including large human interaction forces during the training to further improve control robustness. To evaluate the effectiveness of the learning controller, we conduct numerical experiments with different settings to demonstrate its remarkable ability on controlling the exoskeleton to repetitively perform well balanced and robust squatting motions under strong perturbations and realistic human interaction forces.

Reinforcement Learning and Control of a Lower Extremity Exoskeleton for Squat Assistance

Crowdsourcing has become an important tool to aggregate the wisdom of the crowd in this Internet age. A central problem in building an online crowdsourcing system is to determine the appropriate number of workers to assign tasks to. We study this problem by formulating a Bayes Net framework and introduce a quantity derived from posterior distribution to measure the convergence of crowd opinions. Using this quantity, our algorithm could stop soliciting opinions from more workers if the distribution of opinions is unlikely to change in future predictions. We empirically demonstrate the effectiveness of the designed strategy by building a challenging fine-grained image annotation task on Amazon Mechanical Turk. Experiment results show that our approach not only saves annotation cost but also guarantees high annotation quality.

Efficient Crowdsourcing via Bayes Quality Control

We propose a teleoperation system that uses a single RGB-D camera as the human motion capture device. Our system can perform general manipulation tasks such as cloth folding, hammering and 3mm clearance peg in hole. We propose the use of non-Cartesian oblique coordinate frame, dynamic motion scaling and reposition of operator frames to increase the flexibility of our teleoperation system. We hypothesize that lowering the barrier of entry to teleoperation will allow for wider deployment of supervised autonomy system, which will in turn generates realistic datasets that unlock the potential of machine learning for robotic manipulation.

Hao Su

Papers

Synthesis of high-strength porous particles based on alkaline solid waste: a promising CO2-capturing material for mine goafs

LESS: Label-Eﬃcient Semantic Segmentation for LiDAR Point Clouds

Reinforcement Learning and Control of a Lower Extremity Exoskeleton for Squat Assistance

Efficient Crowdsourcing via Bayes Quality Control

Single RGB-D Camera Teleoperation for General Robotic Manipulation.