Krishna Prasad Miyapuram

Prajwal Singh, Dwip Dalal, Gautam Vashishtha et al.

Decoding the human brain has been a hallmark of neuroscientists and Artificial Intelligence researchers alike. Reconstruction of visual images from brain Electroencephalography (EEG) signals has garnered a lot of interest due to its applications in brain-computer interfacing. This study proposes a two-stage method where the first step is to obtain EEG-derived features for robust learning of deep representations and subsequently utilize the learned representation for image generation and classification. We demonstrate the generalizability of our feature extraction pipeline across three different datasets using deep-learning architectures with supervised and contrastive learning methods. We have performed the zero-shot EEG classification task to support the generalizability claim further. We observed that a subject invariant linearly separable visual representation was learned using EEG data alone in an unimodal setting that gives better k-means accuracy as compared to a joint representation learning between EEG and images. Finally, we propose a novel framework to transform unseen images into the EEG space and reconstruct them with approximation, showcasing the potential for image reconstruction from EEG signals. Our proposed image synthesis method from EEG shows 62.9% and 36.13% inception score improvement on the EEGCVPR40 and the Thoughtviz datasets, which is better than state-of-the-art performance in GAN.

Sudip Das, Pankaj Pandey, Krishna Prasad Miyapuram

There is abundant medical data on the internet, most of which are unlabeled. Traditional supervised learning algorithms are often limited by the amount of labeled data, especially in the medical domain, where labeling is costly in terms of human processing and specialized experts needed to label them. They are also prone to human error and biased as a select few expert annotators label them. These issues are mitigated by Self-supervision, where we generate pseudo-labels from unlabelled data by seeing the data itself. This paper presents various self-supervision strategies to enhance the performance of a time-series based Diffusion convolution recurrent neural network (DCRNN) model. The learned weights in the self-supervision pretraining phase can be transferred to the supervised training phase to boost the model's prediction capability. Our techniques are tested on an extension of a Diffusion Convolutional Recurrent Neural network (DCRNN) model, an RNN with graph diffusion convolutions, which models the spatiotemporal dependencies present in EEG signals. When the learned weights from the pretraining stage are transferred to a DCRNN model to determine whether an EEG time window has a characteristic seizure signal associated with it, our method yields an AUROC score $1.56\%$ than the current state-of-the-art models on the TUH EEG seizure corpus.

Anupam Sharma, Harish Katti, Prajwal Singh et al.

An electroencephalogram (EEG) records the spatially averaged electrical activity of neurons in the brain, measured from the human scalp. Prior studies have explored EEG-based classification of objects or concepts, often for passive viewing of briefly presented image or video stimuli, with limited classes. Because EEG exhibits a low signal-to-noise ratio, recognizing fine-grained representations across a large number of classes remains challenging; however, abstract-level object representations may exist. In this work, we investigate whether EEG captures object representations across multiple hierarchical levels, and propose episodic analysis, in which a Machine Learning (ML) model is evaluated across various, yet related, classification tasks (episodes). Unlike prior episodic EEG studies that rely on fixed or randomly sampled classes of equal cardinality, we adopt hierarchy-aware episode sampling using WordNet to generate episodes with variable classes of diverse hierarchy. We also present the largest episodic framework in the EEG domain for detecting observed text from EEG signals in the PEERS dataset, comprising $931538$ EEG samples under $1610$ object labels, acquired from $264$ human participants (subjects) performing controlled cognitive tasks, enabling the study of neural dynamics underlying perception, decision-making, and performance monitoring. We examine how the semantic abstraction level affects classification performance across multiple learning techniques and architectures, providing a comprehensive analysis. The models tend to improve performance when the classification categories are drawn from higher levels of the hierarchy, suggesting sensitivity to abstraction. Our work highlights abstraction depth as an underexplored dimension of EEG decoding and motivates future research in this direction.

Shriraj P. Sawant, Krishna P. Miyapuram

The ability to learn and retain a wide variety of tasks is a hallmark of human intelligence that has inspired research in artificial general intelligence. Continual learning approaches provide a significant step towards achieving this goal. It has been known that task variability and context switching are challenging for learning in neural networks. Catastrophic forgetting refers to the poor performance on retention of a previously learned task when a new task is being learned. Switching between different task contexts can be a useful approach to mitigate the same by preventing the interference between the varying task weights of the network. This paper introduces Elastic Weight Generative Networks (EWGN) as an idea for context switching between two different tasks. The proposed EWGN architecture uses an additional network that generates the weights of the primary network dynamically while consolidating the weights learned. The weight generation is input-dependent and thus enables context switching. Using standard computer vision datasets, namely MNIST and fashion-MNIST, we analyse the retention of previously learned task representations in Fully Connected Networks, Convolutional Neural Networks, and EWGN architectures with Stochastic Gradient Descent and Elastic Weight Consolidation learning algorithms. Understanding dynamic weight generation and context-switching ability can be useful in enabling continual learning for improved performance.

Anupam Sharma, Krishna Miyapuram

Electroencephalography (EEG) classification is a versatile and portable technique for building non-invasive Brain-computer Interfaces (BCI). However, the classifiers that decode cognitive states from EEG brain data perform poorly when tested on newer domains, such as tasks or individuals absent during model training. Researchers have recently used complex strategies like Model-agnostic meta-learning (MAML) for domain adaptation. Nevertheless, there is a need for an evaluation strategy to evaluate the fast adaptability of the models, as this characteristic is essential for real-life BCI applications for quick calibration. We used motor movement and imaginary signals as input to Convolutional Neural Networks (CNN) based classifier for the experiments. Datasets with EEG signals typically have fewer examples and higher time resolution. Even though batch-normalization is preferred for Convolutional Neural Networks (CNN), we empirically show that layer-normalization can improve the adaptability of CNN-based EEG classifiers with not more than ten fine-tuning steps. In summary, the present work (i) proposes a simple strategy to evaluate fast adaptability, and (ii) empirically demonstrate fast adaptability across individuals as well as across tasks with simple transfer learning as compared to MAML approach.

Krishna Prasad Miyapuram, Wolfram Schultz, Philippe N. Tobler

Mental imagery refers to percept-like experiences in the absence of sensory input. Brain imaging studies suggest common, modality-specific, neural correlates imagery and perception. We associated abstract visual stimuli with either visually presented or imagined monetary rewards and scrambled pictures. Brain images for a group of 12 participants were collected using functional magnetic resonance imaging. Statistical analysis showed that human midbrain regions were activated irrespective of the monetary rewards being imagined or visually present. A support vector machine trained on the midbrain activation patterns to the visually presented rewards predicted with 75% accuracy whether the participants imagined the monetary reward or the scrambled picture during imagination trials. Training samples were drawn from visually presented trials and classification accuracy was assessed for imagination trials. These results suggest the use of machine learning technique for classification of underlying cognitive states from brain imaging data.

Pankaj Pandey, Krishna Prasad Miyapuram

Several Convolutional Deep Learning models have been proposed to classify the cognitive states utilizing several neuro-imaging domains. These models have achieved significant results, but they are heavily designed with millions of parameters, which increases train and test time, making the model complex and less suitable for real-time analysis. This paper proposes a simple, lightweight CNN model to classify cognitive states from Electroencephalograph (EEG) recordings. We develop a novel pipeline to learn distinct cognitive representation consisting of two stages. The first stage is to generate the 2D spectral images from neural time series signals in a particular frequency band. Images are generated to preserve the relationship between the neighboring electrodes and the spectral property of the cognitive events. The second is to develop a time-efficient, computationally less loaded, and high-performing model. We design a network containing 4 blocks and major components include standard and depth-wise convolution for increasing the performance and followed by separable convolution to decrease the number of parameters which maintains the tradeoff between time and performance. We experiment on open access EEG meditation dataset comprising expert, nonexpert meditative, and control states. We compare performance with six commonly used machine learning classifiers and four state of the art deep learning models. We attain comparable performance utilizing less than 4\% of the parameters of other models. This model can be employed in a real-time computation environment such as neurofeedback.

Prashant Lawhatre, Bharatesh R Shiraguppi, Esha Sharma et al.

This research study aims to use machine learning methods to characterize the EEG response to music. Specifically, we investigate how resonance in the EEG response correlates with individual aesthetic enjoyment. Inspired by the notion of musical processing as resonance, we hypothesize that the intensity of an aesthetic experience is based on the degree to which a participants EEG entrains to the perceptual input. To test this and other hypotheses, we have built an EEG dataset from 20 subjects listening to 12 two minute-long songs in random order. After preprocessing and feature construction, we used this dataset to train and test multiple machine learning models.

Dhananjay Sonawane, Krishna Prasad Miyapuram, Bharatesh RS et al.

The music signal comprises of different features like rhythm, timbre, melody, harmony. Its impact on the human brain has been an exciting research topic for the past several decades. Electroencephalography (EEG) signal enables non-invasive measurement of brain activity. Leveraging the recent advancements in deep learning, we proposed a novel approach for song identification using a Convolution Neural network given the electroencephalography (EEG) responses. We recorded the EEG signals from a group of 20 participants while listening to a set of 12 song clips, each of approximately 2 minutes, that were presented in random order. The repeating nature of Music is captured by a data slicing approach considering brain signals of 1 second duration as representative of each song clip. More specifically, we predict the song corresponding to one second of EEG data when given as input rather than a complete two-minute response. We have also discussed pre-processing steps to handle large dimensions of a dataset and various CNN architectures. For all the experiments, we have considered each participant's EEG response for each song in both train and test data. We have obtained 84.96\% accuracy for the same. The performance observed gives appropriate implication towards the notion that listening to a song creates specific patterns in the brain, and these patterns vary from person to person.

Pankaj Pandey, Raunak Swarnkar, Shobhit Kakaria et al.

Neuromarketing aims to understand consumer behavior using neuroscience. Brain imaging tools such as EEG have been used to better understand consumer behavior that goes beyond self-report measures which can be a more accurate measure to understand how and why consumers prefer choosing one product over another. Previous studies have shown that consumer preferences can be effectively predicted by understanding changes in evoked responses as captured by EEG. However, understanding ordered preference of choices was not studied earlier. In this study, we try to decipher the evoked responses using EEG while participants were presented with naturalistic stimuli i.e. movie trailers. Using Machine Learning tech niques to mine the patterns in EEG signals, we predicted the movie rating with more than above-chance, 72% accuracy. Our research shows that neural correlates can be an effective predictor of consumer choices and can significantly enhance our understanding of consumer behavior.

Prakash Rajan, Krishna P. Miyapuram

There is a sudden surge to model human behavior due to its vast and diverse applications which includes modeling public policies, economic behavior and consumer behavior. Most of the human behavior itself can be modeled into a choice prediction problem. Prospect theory is a theoretical model that tries to explain the anomalies in choice prediction. These theories perform well in terms of explaining the anomalies but they lack precision. Since the behavior is person dependent, there is a need to build a model that predicts choices on a per-person basis. Looking on at the average persons choice may not necessarily throw light on a particular person's choice. Modeling the gambling problem on a per person basis will help in recommendation systems and related areas. A novel hybrid model namely psychological factorisation machine ( PsychFM ) has been proposed that involves concepts from machine learning as well as psychological theories. It outperforms the popular existing models namely random forest and factorisation machines for the benchmark dataset CPC-18. Finally,the efficacy of the proposed hybrid model has been verified by comparing with the existing models.

Shubham Kumar Singh, Krishna P Miyapuram, Shanmuganathan Raman

Person re-identification aims to associate images of the same person over multiple non-overlapping camera views at different times. Depending on the human operator, manual re-identification in large camera networks is highly time consuming and erroneous. Automated person re-identification is required due to the extensive quantity of visual data produced by rapid inflation of large scale distributed multi-camera systems. The state-of-the-art works focus on learning and factorize person appearance features into latent discriminative factors at multiple semantic levels. We propose Deep Parallel Feature Consensus Network (DeepPFCN), a novel network architecture that learns multi-scale person appearance features using convolutional neural networks. This model factorizes the visual appearance of a person into latent discriminative factors at multiple semantic levels. Finally consensus is built. The feature representations learned by DeepPFCN are more robust for the person re-identification task, as we learn discriminative scale-specific features and maximize multi-scale feature fusion selections in multi-scale image inputs. We further exploit average and max pooling in separate scale for person-specific task to discriminate features globally and locally. We demonstrate the re-identification advantages of the proposed DeepPFCN model over the state-of-the-art re-identification methods on three benchmark datasets: Market1501, DukeMTMCreID, and CUHK03. We have achieved mAP results of 75.8%, 64.3%, and 52.6% respectively on these benchmark datasets.

Viraj Mavani, Shanmuganathan Raman, Krishna P Miyapuram

We have developed a convolutional neural network for the purpose of recognizing facial expressions in human beings. We have fine-tuned the existing convolutional neural network model trained on the visual recognition dataset used in the ILSVRC2012 to two widely used facial expression datasets - CFEE and RaFD, which when trained and tested independently yielded test accuracies of 74.79% and 95.71%, respectively. Generalization of results was evident by training on one dataset and testing on the other. Further, the image product of the cropped faces and their visual saliency maps were computed using Deep Multi-Layer Network for saliency prediction and were fed to the facial expression recognition CNN. In the most generalized experiment, we observed the top-1 accuracy in the test set to be 65.39%. General confusion trends between different facial expressions as exhibited by humans were also observed.