We investigate novel parameter estimation and goodness-of-fit (GOF) assessment methods for large-scale confirmatory item factor analysis (IFA) with many respondents, items, and latent factors. For parameter estimation, we extend Urban and Bauer's (2021) deep learning algorithm for exploratory IFA to the confirmatory setting by showing how to handle user-defined constraints on loadings and factor correlations. For GOF assessment, we explore new simulation-based tests and indices. In particular, we consider extensions of the classifier two-sample test (C2ST), a method that tests whether a machine learning classifier can distinguish between observed data and synthetic data sampled from a fitted IFA model. The C2ST provides a flexible framework that integrates overall model fit, piece-wise fit, and person fit. Proposed extensions include a C2ST-based test of approximate fit in which the user specifies what percentage of observed data can be distinguished from synthetic data as well as a C2ST-based relative fit index that is similar in spirit to the relative fit indices used in structural equation modeling. Via simulation studies, we first show that the confirmatory extension of Urban and Bauer's (2021) algorithm produces more accurate parameter estimates as the sample size increases and obtains comparable estimates to a state-of-the-art confirmatory IFA estimation procedure in less time. We next show that the C2ST-based test of approximate fit controls the empirical type I error rate and detects when the number of latent factors is misspecified. Finally, we empirically investigate how the sampling distribution of the C2ST-based relative fit index depends on the sample size.

Despite impressive state-of-the-art performance on a wide variety of machine learning tasks in multiple applications, deep learning methods can produce over-confident predictions, particularly with limited training data. Therefore, quantifying uncertainty is particularly important in critical applications such as anomaly or lesion detection and clinical diagnosis, where a realistic assessment of uncertainty is essential in determining surgical margins, disease status and appropriate treatment. In this work, we focus on using quantile regression to estimate aleatoric uncertainty and use it for estimating uncertainty in both supervised and unsupervised lesion detection problems. In the unsupervised settings, we apply quantile regression to a lesion detection task using Variational AutoEncoder (VAE). The VAE models the output as a conditionally independent Gaussian characterized by means and variances for each output dimension. Unfortunately, joint optimization of both mean and variance in the VAE leads to the well-known problem of shrinkage or underestimation of variance. We describe an alternative VAE model, Quantile-Regression VAE (QR-VAE), that avoids this variance shrinkage problem by estimating conditional quantiles for the given input image. Using the estimated quantiles, we compute the conditional mean and variance for input images under the conditionally Gaussian model. We then compute reconstruction probability using this model as a principled approach to outlier or anomaly detection applications. In the supervised setting, we develop binary quantile regression (BQR) for the supervised lesion segmentation task. BQR segmentation can capture uncertainty in label boundaries. We show how quantile regression can be used to characterize expert disagreement in the location of lesion boundaries.

Since the development of generic language models trained on massive unlabelled text corpora (Radford et al., 2019; Brown et al., 2020), state-of-the art language processing systems rely on sequential transfer learning (Ruder, 2019). The pretrained Language Model (LM) is fine-tuned on the downstream task using a standard supervised learning (SL) objective (Wu et al., 2019; Peters et al., 2019). Yet, such an approach suffers from several issues (Chen et al., 2020): (i) catastrophic forgetting when a model forgets previously learned knowledge and overfits to target domains, (ii) computational inefficiency from fine-tuning billionparameters networks, and (iii) the need of supervised datasets. Moreover, task-specific language models learned with SL suffer from well-studied text degeneration issues (Holtzman et al., 2019), such as the exposure bias (Bengio et al., 2015), language biases (Saleh et al., 2020; Jaques et al., 2020), or a lack of diversity (Li et al., 2015). On the other hand, text generation can be naturally framed as a sequential decision making problem, with the sequence of words seen as successive actions over a vocabulary. Thus, some researchers have recently focused on learning language models using instead Reinforcement Learning (RL) (Strub et al., 2017; Das et al., 2017; Narasimhan et al., 2015).

This timeline shows the fundamental studies that were done in artificial intelligence. While researchers tried to mimic the neurons between the 50s-70s, they focused on machine learning with expert systems. Beginning from the 2000s, the focus is currently on deep learning studies. As I mentioned, all of these domains are part of artificial intelligence. Let's talk more about these relevant domains… Machine learning is considered as a sub-discipline under the field of artificial intelligence.

"Somethings never change, their essence and contributions remain the same till date". Through this line I am pointing out the millennia-old contribution of books in educating people; even to this date, we are heavily dependant on text, papers, books. I was always a video lecture type of person, they seem less boring on to the point, but my opinion drastically changed once I discovered these books on Deep learning by these elite publishers. For the longest, I thought books are not a good option to study such complex mathematical and computer science concepts, but I am glad to be proven wrong by these books. The books mentioned here are a few out of all; that I have gone through.

It's likely no surprise that women are still massively underrepresented in the tech industry today. Even with a push over the last few years for more women to pursue careers in STEM--science, technology, engineering, and mathematics--they still make up a tiny percentage of those working in the field. Data shows that of those doing STEM-focused research around the world, less than 30% are women. Unfortunately, when you narrow the focus down to women working specifically in smart tech and machine learning, the numbers get even smaller. You might wonder why it matters who is behind the data and code creation when it's essentially a non-gendered machine or robot doing all of the processing, but it does.

Today, GPUs are found in almost all imaging modalities, including CT, MRI, x-ray, and ultrasound - bringing compute capabilities to the edge devices. With the boom of deep learning research in medical imaging, more efficient and improved approaches are being developed to enable AI-assisted workflows. To develop these AI capable applications, the data needs to be made AI-ready. NVIDIA Clara's AI-Assisted Annotation does so by providing APIs and a toolkit to bring AI-assisted annotation capabilities to any medical viewer. Post annotation, data scientists and researchers need to build a robust AI model.

BERT is a state-of-the-art model by Google that came in 2019. In this blog, I will go step by step to finetune the BERT model for movie reviews classification(i.e positive or negative). Here, I will be using the Pytorch framework for the coding perspective. BERT is built on top of the transformer (explained in paper Attention is all you Need). Input text sentences would first be tokenized into words, then the special tokens ( [CLS], [SEP], ##token) will be added to the sequence of words.

Fake images and videos have engulfed mass communication media. This is not something recent, manipulations and forgeries have occurred since the advent of photography itself. These alterations can go from innocent retouches in an attempt to make an image visually attractive to the spread of misleading information or even the use of false media in legal instances. Accordingly, the creation of methods that can help us assure the authenticity of an image presented as non-modified is of paramount importance. In this thesis, we aim at detecting image manipulation operations using deep learning techniques. We present three methods showing the progression of our work under one common objective, i.e, the design and test of Convolutional Neural Network (CNN) initialization methods for image forensic problems with a variance stability focus for the output of a CNN layer.First, we carry out an extensive review of the state of the art in deep-learning-based methods for image forensics. From this review we can confirm that the first layer of a CNN has big impact on the final performance. Specifically, the initialization used on the first-layer filters plays an important role that should be in line with the image forensic task in hand.As our first attempt to address this research problem, we propose a low-complexity initialization method for CNNs. Taking advantage of previous methods designed for the computer vision field, we extend the popular Xavier method to design a filter that would provide variance stability after a convolution operation. This method generates a set of random high-pass filters for the initialization of a CNN's first layer. These filters allow us to better identify forensic traces which usually lie towards the high-frequency part of the image.This first approach constitutes a good staring point of our work. However, a wrong assumption, largely utilized in the research community, was made. This is corrected in our second method where we follow a different data-dependent approach and take into consideration the real statistical properties of natural images. Accordingly, we propose a scaling method for first-layer filters which can cope well with different CNN initialization algorithms. The objective remains in keeping the stability of the variance of data flow in a CNN. We also present theoretical and experimental studies on the output variance for convolutional filter, which are the basis of our proposed data-dependent scaling.Next we describe a revisited version of our first proposal now with a corrected assumption on the statistics of natural images. More precisely, we propose an improved random high-pass initialization method which does not explicitly compute the statistics of input data. We believe that such a ``data-independent'' approach has higher flexibility and broader application range than our second method in situations where the computation of input statistics is not possible.Our proposed methods are tested over several image forensic problems and different CNN architectures.Finally, during all this thesis work we took part in a challenge competition of image forgery detection organized by the French National Research Agency and the French Directorate General of Armaments. We explain in the Appendix the objectives of the challenge along with a brief description of our work conducted for the competition.

Lets discuss Regularizing Deep Neural Networks. Deep neural nets with an outsized number of parameters are very powerful machine learning systems. However, overfitting may be a significant issue in such networks. Making it hard to affect over-fitting by associating the predictions of the many different large neural nets at test time, big networks similarly are slow to use. Dropout might be a technique for addressing this problem.