기법

BCI MI framework to classifiy brain signals using a multimodal decission making phase, with an addtional differentiation of the signal.

We present a novel classifier network called STEP, to classify perceived human emotion from gaits, based on a Spatial Temporal Graph Convolutional Network (ST-GCN) architecture. Given an RGB video of an individual walking, our formulation implicitly exploits the gait features to classify the perceived emotion of the human into one of four emotions: happy, sad, angry, or neutral. We train STEP on annotated real-world gait videos, augmented with annotated synthetic gaits generated using a novel generative network called STEP-Gen, built on an ST-GCN based Conditional Variational Autoencoder (CVAE). We incorporate a novel push-pull regularization loss in the CVAE formulation of STEP-Gen to generate realistic gaits and improve the classification accuracy of STEP. We also release a novel dataset (E-Gait), which consists of 4,227 human gaits annotated with perceived emotions along with thousands of synthetic gaits. In practice, STEP can learn the affective features and exhibits classification accuracy of 88% on E-Gait, which is 14--30% more accurate over prior methods.

Inception-ResNet-v2 Reduction-B is an image model block used in the Inception-ResNet-v2 architecture.

Inception-ResNet-v2-B is an image model block for a 17 x 17 grid used in the Inception-ResNet-v2 architecture. It largely follows the idea of Inception modules - and grouped convolutions - but also includes residual connections.

Inception-ResNet-v2-C is an image model block for an 8 x 8 grid used in the Inception-ResNet-v2 architecture. It largely follows the idea of Inception modules - and grouped convolutions - but also includes residual connections.

LSGAN, or Least Squares GAN, is a type of generative adversarial network that adopts the least squares loss function for the discriminator. Minimizing the objective function of LSGAN yields minimizing the Pearson $\chi^{2}$ divergence. The objective function can be defined as: $$ \min\_{D}V\_{LSGAN}\left(D\right) = \frac{1}{2}\mathbb{E}\_{\mathbf{x} \sim p\_{data}\left(\mathbf{x}\right)}\left[\left(D\left(\mathbf{x}\right) - b\right)^{2}\right] + \frac{1}{2}\mathbb{E}\_{\mathbf{z}\sim p\_{\mathbf{z}}\left(\mathbf{z}\right)}\left[\left(D\left(G\left(\mathbf{z}\right)\right) - a\right)^{2}\right] $$ $$ \min\_{G}V\_{LSGAN}\left(G\right) = \frac{1}{2}\mathbb{E}\_{\mathbf{z} \sim p\_{\mathbf{z}}\left(\mathbf{z}\right)}\left[\left(D\left(G\left(\mathbf{z}\right)\right) - c\right)^{2}\right] $$ where $a$ and $b$ are the labels for fake data and real data and $c$ denotes the value that $G$ wants $D$ to believe for fake data.

Neural Additive Models (NAMs) make restrictions on the structure of neural networks, which yields a family of models that are inherently interpretable while suffering little loss in prediction accuracy when applied to tabular data. Methodologically, NAMs belong to a larger model family called Generalized Additive Models (GAMs). NAMs learn a linear combination of networks that each attend to a single input feature: each $f\_{i}$ in the traditional GAM formulationis parametrized by a neural network. These networks are trained jointly using backpropagation and can learn arbitrarily complex shape functions. Interpreting NAMs is easy as the impact of a feature on the prediction does not rely on the other features and can be understood by visualizing its corresponding shape function (e.g., plotting $f\_{i}\left(x\_{i}\right)$ vs. $x\_{i}$).

Path Aggregation Network, or PANet, aims to boost information flow in a proposal-based instance segmentation framework. Specifically, the feature hierarchy is enhanced with accurate localization signals in lower layers by bottom-up path augmentation, which shortens the information path between lower layers and topmost feature. Additionally, adaptive feature pooling is employed, which links feature grid and all feature levels to make useful information in each feature level propagate directly to following proposal subnetworks. A complementary branch capturing different views for each proposal is created to further improve mask prediction.

Population Based Training, or PBT, is an optimization method for finding parameters and hyperparameters, and extends upon parallel search methods and sequential optimisation methods. It leverages information sharing across a population of concurrently running optimisation processes, and allows for online propagation/transfer of parameters and hyperparameters between members of the population based on their performance. Furthermore, unlike most other adaptation schemes, the method is capable of performing online adaptation of hyperparameters -- which can be particularly important in problems with highly non-stationary learning dynamics, such as reinforcement learning settings. PBT is decentralised and asynchronous, although it could also be executed semi-serially or with partial synchrony if there is a binding budget constraint.

Self-Cure Network, or SCN, is a method for suppressing uncertainties for large-scale facial expression recognition, prventing deep networks from overfitting uncertain facial images. Specifically, SCN suppresses the uncertainty from two different aspects: 1) a self-attention mechanism over mini-batch to weight each training sample with a ranking regularization, and 2) a careful relabeling mechanism to modify the labels of these samples in the lowest-ranked group.

TimeSformer is a convolution-free approach to video classification built exclusively on self-attention over space and time. It adapts the standard Transformer architecture to video by enabling spatiotemporal feature learning directly from a sequence of frame-level patches. Specifically, the method adapts the image model [Vision Transformer](https//www.paperswithcode.com/method/vision-transformer) (ViT) to video by extending the self-attention mechanism from the image space to the space-time 3D volume. As in ViT, each patch is linearly mapped into an embedding and augmented with positional information. This makes it possible to interpret the resulting sequence of vector

The Universal Transformer is a generalization of the Transformer architecture. Universal Transformers combine the parallelizability and global receptive field of feed-forward sequence models like the Transformer with the recurrent inductive bias of RNNs. They also utilise a dynamic per-position halting mechanism.

A (2+1)D Convolution is a type of convolution used for action recognition convolutional neural networks, with a spatiotemporal volume. As opposed to applying a 3D Convolution over the entire volume, which can be computationally expensive and lead to overfitting, a (2+1)D convolution splits computation into two convolutions: a spatial 2D convolution followed by a temporal 1D convolution.

ALBEF introduces a contrastive loss to align the image and text representations before fusing them through cross-modal attention. This enables more grounded vision and language representation learning. ALBEF also doesn't require bounding box annotations. The model consists of an image encode, a text encoder, and a multimodal encoder. The image-text contrastive loss helps to align the unimodal representations of an image-text pair before fusion. The image-text matching loss and a masked language modeling loss are applied to learn multimodal interactions between image and text. In addition, momentum distillation is used to generate pseudo-targets. This improves learning with noisy data.

AdaDelta is a stochastic optimization technique that allows for per-dimension learning rate method for SGD. It is an extension of Adagrad that seeks to reduce its aggressive, monotonically decreasing learning rate. Instead of accumulating all past squared gradients, Adadelta restricts the window of accumulated past gradients to a fixed size $w$. Instead of inefficiently storing $w$ previous squared gradients, the sum of gradients is recursively defined as a decaying average of all past squared gradients. The running average $E\left[g^{2}\right]\_{t}$ at time step $t$ then depends only on the previous average and current gradient: $$E\left[g^{2}\right]\_{t} = \gamma{E}\left[g^{2}\right]\_{t-1} + \left(1-\gamma\right)g^{2}\_{t}$$ Usually $\gamma$ is set to around $0.9$. Rewriting SGD updates in terms of the parameter update vector: $$ \Delta\theta_{t} = -\eta\cdot{g\_{t, i}}$$ $$\theta\_{t+1} = \theta\_{t} + \Delta\theta_{t}$$ AdaDelta takes the form: $$ \Delta\theta_{t} = -\frac{\eta}{\sqrt{E\left[g^{2}\right]\_{t} + \epsilon}}g_{t} $$ The main advantage of AdaDelta is that we do not need to set a default learning rate.

Iterative Pseudo-Labeling (IPL) is a semi-supervised algorithm for speech recognition which efficiently performs multiple iterations of pseudo-labeling on unlabeled data as the acoustic model evolves. In particular, IPL fine tunes an existing model at each iteration using both labeled data and a subset of unlabeled data.

Local Prior Matching is a semi-supervised objective for speech recognition that distills knowledge from a strong prior (e.g. a language model) to provide learning signal to a discriminative model trained on unlabeled speech. The LPM objective minimizes the cross entropy between the local prior and the model distribution, and is minimized when $q\_{y\mid{x}} = \bar{p}\_{y\mid{x}}$. Intuitively, LPM encourages the ASR model to assign posterior probabilities proportional to the linguistic probabilities of the proposed hypotheses.

Linformer is a linear Transformer that utilises a linear self-attention mechanism to tackle the self-attention bottleneck with Transformer models. The original scaled dot-product attention is decomposed into multiple smaller attentions through linear projections, such that the combination of these operations forms a low-rank factorization of the original attention.

MPNet is a pre-training method for language models that combines masked language modeling (MLM) and permuted language modeling (PLM) in one view. It takes the dependency among the predicted tokens into consideration through permuted language modeling and thus avoids the issue of BERT. On the other hand, it takes position information of all tokens as input to make the model see the position information of all the tokens and thus alleviates the position discrepancy of XLNet. The training objective of MPNet is: $$ \mathbb{E}\_{z\in{\mathcal{Z}\_{n}}} \sum^{n}\_{t=c+1}\log{P}\left(x\_{z\_{t}}\mid{x\_{z\_{<t}}}, M\_{z\_{{>}{c}}}; \theta\right) $$ As can be seen, MPNet conditions on ${x\_{z\_{<t}}}$ (the tokens preceding the current predicted token $x\_{z\_{t}}$) rather than only the non-predicted tokens ${x\_{z\_{<=c}}}$ in MLM; comparing with PLM, MPNet takes more information (i.e., the mask symbol $[M]$ in position $z\_{>c}$) as inputs. Although the objective seems simple, it is challenging to implement the model efficiently. For details, see the paper.

PrIme Sample Attention (PISA) directs the training of object detection frameworks towards prime samples. These are samples that play a key role in driving the detection performance. The authors define Hierarchical Local Rank (HLR) as a metric of importance. Specifically, they use IoU-HLR to rank positive samples and ScoreHLR to rank negative samples in each mini-batch. This ranking strategy places the positive samples with highest IoUs around each object and the negative samples with highest scores in each cluster to the top of the ranked list and directs the focus of the training process to them via a simple re-weighting scheme. The authors also devise a classification-aware regression loss to jointly optimize the classification and regression branches. Particularly, this loss would suppress those samples with large regression loss, thus reinforcing the attention to prime samples.

ProxylessNAS directly learns neural network architectures on the target task and target hardware without any proxy task. Additional contributions include: - Using a new path-level pruning perspective for neural architecture search, showing a close connection between NAS and model compression. Memory consumption is saved by one order of magnitude by using path-level binarization. - Using a novel gradient-based approach (latency regularization loss) for handling hardware objectives (e.g. latency). Given different hardware platforms: CPU/GPU/Mobile, ProxylessNAS enables hardware-aware neural network specialization that’s exactly optimized for the target hardware.

SNIP, or Scale Normalization for Image Pyramids, is a multi-scale training scheme that selectively back-propagates the gradients of object instances of different sizes as a function of the image scale. SNIP is a modified version of MST where only the object instances that have a resolution close to the pre-training dataset, which is typically 224x224, are used for training the detector. In multi-scale training (MST), each image is observed at different resolutions therefore, at a high resolution (like 1400x2000) large objects are hard to classify and at a low resolution (like 480x800) small objects are hard to classify. Fortunately, each object instance appears at several different scales and some of those appearances fall in the desired scale range. In order to eliminate extreme scale objects, either too large or too small, training is only performed on objects that fall in the desired scale range and the remainder are simply ignored during back-propagation. Effectively, SNIP uses all the object instances during training, which helps capture all the variations in appearance and pose, while reducing the domain-shift in the scale-space for the pre-trained network.

Stable Rank Normalization (SRN) is a weight-normalization scheme which minimizes the stable rank of a linear operator. It simultaneously controls the Lipschitz constant and the stable rank of a linear operator. Stable rank is a softer version of the rank operator and is defined as the squared ratio of the Frobenius norm to the spectral norm.

BigBird is a Transformer with a sparse attention mechanism that reduces the quadratic dependency of self-attention to linear in the number of tokens. BigBird is a universal approximator of sequence functions and is Turing complete, thereby preserving these properties of the quadratic, full attention model. In particular, BigBird consists of three main parts: - A set of $g$ global tokens attending on all parts of the sequence. - All tokens attending to a set of $w$ local neighboring tokens. - All tokens attending to a set of $r$ random tokens. This leads to a high performing attention mechanism scaling to much longer sequence lengths (8x).

Chimera is a pipeline model parallelism scheme which combines bidirectional pipelines for efficiently training large-scale models. The key idea of Chimera is to combine two pipelines in different directions (down and up pipelines). Denote $N$ as the number of micro-batches executed by each worker within a training iteration, and $D$ the number of pipeline stages (depth), and $P$ the number of workers. The Figure shows an example with four pipeline stages (i.e. $D=4$). Here we assume there are $D$ micro-batches executed by each worker within a training iteration, namely $N=D$, which is the minimum to keep all the stages active. In the down pipeline, stage$\_{0}$∼stage$\_{3}$ are mapped to $P\_{0}∼P\_{3}$ linearly, while in the up pipeline the stages are mapped in a completely opposite order. The $N$ (assuming an even number) micro-batches are equally partitioned among the two pipelines. Each pipeline schedules $N/2$ micro-batches using 1F1B strategy, as shown in the left part of the Figure. Then, by merging these two pipelines together, we obtain the pipeline schedule of Chimera. Given an even number of stages $D$ (which can be easily satisfied in practice), it is guaranteed that there is no conflict (i.e., there is at most one micro-batch occupies the same time slot on each worker) during merging.

A CoordConv layer is a simple extension to the standard convolutional layer. It has the same functional signature as a convolutional layer, but accomplishes the mapping by first concatenating extra channels to the incoming representation. These channels contain hard-coded coordinates, the most basic version of which is one channel for the $i$ coordinate and one for the $j$ coordinate. The CoordConv layer keeps the properties of few parameters and efficient computation from convolutions, but allows the network to learn to keep or to discard translation invariance as is needed for the task being learned. This is useful for coordinate transform based tasks where regular convolutions can fail.

Decaying Momentum, or Demon, is a stochastic optimizer motivated by decaying the total contribution of a gradient to all future updates. By decaying the momentum parameter, the total contribution of a gradient to all future updates is decayed. A particular gradient term $g\_{t}$ contributes a total of $\eta\sum\_{i}\beta^{i}$ of its "energy" to all future gradient updates, and this results in the geometric sum, $\sum^{\infty}\_{i=1}\beta^{i} = \beta\sum^{\infty}\_{i=0}\beta^{i} = \frac{\beta}{\left(1-\beta\right)}$. Decaying this sum results in the Demon algorithm. Letting $\beta\_{init}$ be the initial $\beta$; then at the current step $t$ with total $T$ steps, the decay routine is given by solving the below for $\beta\_{t}$: $$ \frac{\beta\_{t}}{\left(1-\beta\_{t}\right)} = \left(1-t/T\right)\beta\_{init}/\left(1-\beta\_{init}\right)$$ Where $\left(1-t/T\right)$ refers to the proportion of iterations remaining. Note that Demon typically requires no hyperparameter tuning as it is usually decayed to $0$ or a small negative value at time $T$. Improved performance is observed by delaying the decaying. Demon can be applied to any gradient descent algorithm with a momentum parameter.

Feature Matching is a regularizing objective for a generator in generative adversarial networks that prevents it from overtraining on the current discriminator. Instead of directly maximizing the output of the discriminator, the new objective requires the generator to generate data that matches the statistics of the real data, where we use the discriminator only to specify the statistics that we think are worth matching. Specifically, we train the generator to match the expected value of the features on an intermediate layer of the discriminator. This is a natural choice of statistics for the generator to match, since by training the discriminator we ask it to find those features that are most discriminative of real data versus data generated by the current model. Letting $\mathbf{f}\left(\mathbf{x}\right)$ denote activations on an intermediate layer of the discriminator, our new objective for the generator is defined as: $ ||\mathbb{E}\_{x\sim p\_{data} } \mathbf{f}\left(\mathbf{x}\right) − \mathbb{E}\_{\mathbf{z}∼p\_{\mathbf{z}}\left(\mathbf{z}\right)}\mathbf{f}\left(G\left(\mathbf{z}\right)\right)||^{2}\_{2} $. The discriminator, and hence $\mathbf{f}\left(\mathbf{x}\right)$, are trained as with vanilla GANs. As with regular GAN training, the objective has a fixed point where G exactly matches the distribution of training data.

Go-Explore is a family of algorithms aiming to tackle two challenges with effective exploration in reinforcement learning: algorithms forgetting how to reach previously visited states ("detachment") and from failing to first return to a state before exploring from it ("derailment"). To avoid detachment, Go-Explore builds an archive of the different states it has visited in the environment, thus ensuring that states cannot be forgotten. Starting with an archive beginning with the initial state, the archive is built iteratively. In Go-Explore we: (a) Probabilistically select a state from the archive, preferring states associated with promising cells. (b) Return to the selected state, such as by restoring simulator state or by running a goal-conditioned policy. (c) Explore from that state by taking random actions or sampling from a trained policy. (d) Map every state encountered during returning and exploring to a low-dimensional cell representation. (e) Add states that map to new cells to the archive and update other archive entries.

IMPALA, or the Importance Weighted Actor Learner Architecture, is an off-policy actor-critic framework that decouples acting from learning and learns from experience trajectories using V-trace. Unlike the popular A3C-based agents, in which workers communicate gradients with respect to the parameters of the policy to a central parameter server, IMPALA actors communicate trajectories of experience (sequences of states, actions, and rewards) to a centralized learner. Since the learner in IMPALA has access to full trajectories of experience we use a GPU to perform updates on mini-batches of trajectories while aggressively parallelising all time independent operations. This type of decoupled architecture can achieve very high throughput. However, because the policy used to generate a trajectory can lag behind the policy on the learner by several updates at the time of gradient calculation, learning becomes off-policy. The V-trace off-policy actor-critic algorithm is used to correct for this harmful discrepancy.

Progressive Neural Architecture Search, or PNAS, is a method for learning the structure of convolutional neural networks (CNNs). It uses a sequential model-based optimization (SMBO) strategy, where we search the space of cell structures, starting with simple (shallow) models and progressing to complex ones, pruning out unpromising structures as we go. At iteration $b$ of the algorithm, we have a set of $K$ candidate cells (each of size $b$ blocks), which we train and evaluate on a dataset of interest. Since this process is expensive, PNAS also learns a model or surrogate function which can predict the performance of a structure without needing to train it. We then expand the $K$ candidates of size $b$ into $K' \gg K$ children, each of size $b+1$. The surrogate function is used to rank all of the $K'$ children, pick the top $K$, and then train and evaluate them. We continue in this way until $b=B$, which is the maximum number of blocks we want to use in a cell.