In traditional Machine Learning domains, we usually take a huge dataset which is specific to a particular task and wish to train a model for regression/classification purposes using this dataset. That's radically far from how humans take advantage of their past experiences to learn very quickly a new task from only a handset of examples. Meta-Learning is essentially learning to learn. Formally, it can be defined as using metadata of an algorithm or a model to understand how automatic learning can become flexible in solving learning problems, hence to improve the performance of existing learning algorithms or to learn (induce) the learning algorithm itself. Each learning algorithm is based on a set of assumptions about the data, which is called its inductive bias.

Increasingly, artificial intelligence systems known as deep learning neural networks are used to inform decisions vital to human health and safety, such as in autonomous driving or medical diagnosis. These networks are good at recognizing patterns in large, complex datasets to aid in decision-making. But how do we know they're correct? Alexander Amini and his colleagues at MIT and Harvard University wanted to find out. They've developed a quick way for a neural network to crunch data, and output not just a prediction but also the model's confidence level based on the quality of the available data.

Deep learning refers to a myriad of nuances in our reaction to different situations that are processed and interpreted by machines.

Deep neural networks (DNNs) can learn accurately from large quantities of labeled input data, but DNNs sometimes fail to generalize to test data sampled from different input distributions. Unsupervised Deep Domain Adaptation (DDA) proves useful when no input labels are available, and distribution shifts are observed in the target domain (TD). Experiments are performed on seismic images of the F3 block 3D dataset from offshore Netherlands (source domain; SD) and Penobscot 3D survey data from Canada (target domain; TD). Three geological classes from SD and TD that have similar reflection patterns are considered. In the present study, an improved deep neural network architecture named EarthAdaptNet (EAN) is proposed to semantically segment the seismic images. We specifically use a transposed residual unit to replace the traditional dilated convolution in the decoder block. The EAN achieved a pixel-level accuracy >84% and an accuracy of ~70% for the minority classes, showing improved performance compared to existing architectures. In addition, we introduced the CORAL (Correlation Alignment) method to the EAN to create an unsupervised deep domain adaptation network (EAN-DDA) for the classification of seismic reflections fromF3 and Penobscot. Maximum class accuracy achieved was ~99% for class 2 of Penobscot with >50% overall accuracy. Taken together, EAN-DDA has the potential to classify target domain seismic facies classes with high accuracy.

We present a method to estimate an HDR environment map from a narrow field-of-view LDR camera image in real-time. This enables perceptually appealing reflections and shading on virtual objects of any material finish, from mirror to diffuse, rendered into a real physical environment using augmented reality. Our method is based on our efficient convolutional neural network architecture, EnvMapNet, trained end-to-end with two novel losses, ProjectionLoss for the generated image, and ClusterLoss for adversarial training. Through qualitative and quantitative comparison to state-of-the-art methods, we demonstrate that our algorithm reduces the directional error of estimated light sources by more than 50%, and achieves 3.7 times lower Frechet Inception Distance (FID). We further showcase a mobile application that is able to run our neural network model in under 9 ms on an iPhone XS, and render in real-time, visually coherent virtual objects in previously unseen real-world environments.

It is not dfficult to point out the weaknesses of neural nets and deep learning. Simply put, neural nets are too weak to support general AI. They receive inputs (numbers), perform simple arithmetic operations and produce outputs (numbers). Consequently, they provide only primitive services such as object classifications. Although object classification has some interesting applications, the power of classification is in fact not much compared to all the complex services a human can provide. Complex services - making a coffee, withdrawing money from ATM, etc - are not well supported by neural nets.

The simplicity and expressiveness of a histogram render it a useful feature in different contexts including deep learning. Although the process of computing a histogram is non-differentiable, researchers have proposed differentiable approximations, which have some limitations. A differentiable histogram that directly approximates the hard-binning operation in conventional histograms is proposed. It combines the strength of existing differentiable histograms and overcomes their individual challenges. In comparison to a histogram computed using Numpy, the proposed histogram has an absolute approximation error of 0.000158.

Since the introduction of DQN, a vast majority of reinforcement learning research has focused on reinforcement learning with deep neural networks as function approximators. New methods are typically evaluated on a set of environments that have now become standard, such as Atari 2600 games. While these benchmarks help standardize evaluation, their computational cost has the unfortunate side effect of widening the gap between those with ample access to computational resources, and those without. In this work we argue that, despite the community's emphasis on large-scale environments, the traditional small-scale environments can still yield valuable scientific insights and can help reduce the barriers to entry for underprivileged communities. To substantiate our claims, we empirically revisit the paper which introduced the Rainbow algorithm [Hessel et al., 2018] and present some new insights into the algorithms used by Rainbow.

Probabilistic time-series models become popular in the forecasting field as they help to make optimal decisions under uncertainty. Despite the growing interest, a lack of thorough analysis hinders choosing what is worth applying for the desired task. In this paper, we analyze the performance of three prominent probabilistic time-series models for sales forecasting. To remove the role of random chance in architecture's performance, we make two experimental principles; 1) Large-scale dataset with various cross-validation sets. 2) A standardized training and hyperparameter selection. The experimental results show that a simple Multi-layer Perceptron and Linear Regression outperform the probabilistic models on RMSE without any feature engineering. Overall, the probabilistic models fail to achieve better performance on point estimation, such as RMSE and MAPE, than comparably simple baselines. We analyze and discuss the performances of probabilistic time-series models.

Recent advances in deep learning have made the use of large, deep neural networks with tens of millions of parameters. The sheer size of these networks imposes a challenging computational burden during inference. Existing work focuses primarily on accelerating each forward pass of a neural network. Inspired by the group testing strategy for efficient disease testing, we propose neural group testing, which accelerates by testing a group of samples in one forward pass. Groups of samples that test negative are ruled out. If a group tests positive, samples in that group are then retested adaptively. A key challenge of neural group testing is to modify a deep neural network so that it could test multiple samples in one forward pass. We propose three designs to achieve this without introducing any new parameters and evaluate their performances. We applied neural group testing in an image moderation task to detect rare but inappropriate images. We found that neural group testing can group up to 16 images in one forward pass and reduce the overall computation cost by over 73% while improving detection performance.