Speaking at KnowDis Machine Learning Day, Avantika Lal - Senior Scientist (Deep Learning and Genomics) at NVIDIA - said larger data sets on genome sequences (DNA arrangement) are being acquired, and this data is being studied for multiple parameters. "As the cost of sequencing goes down, more and more people can get their genome sequence and in fact, governments, research institutes and public health organisations around the world are trying to sequence many thousands of people in order to be build up an idea of the genomes of the populations of their countries," she said. Lal added that massive data sets are collected that are very complicated and contain many different related kinds of information. "...the size and richness of the data sets that we''re now getting in this field makes it really essential to use machine learning and deep learning to analyze this data in order to answer complicated questions like, for example, how do we identify people who are more at risk of developing various diseases before they actually develop signs of those diseases," she said. These data sets can also help understand the mechanisms by which a certain disease arises in people, or how does one identify patients who might respond differently or be more sensitive to a particular kind of drug or treatment, she further said.

Artificial intelligence (AI) and machine learning are helping analyse massive amounts of data around the human genome and drug molecules, and these new-age technologies can play an important role in the fight against Covid-19, industry experts said on Saturday. Speaking at KnowDis Machine Learning Day, Avantika Lal - Senior Scientist (Deep Learning and Genomics) at NVIDIA - said larger data sets on genome sequences (DNA arrangement) are being acquired, and this data is being studied for multiple parameters. "As the cost of sequencing goes down, more and more people can get their genome sequence and in fact, governments, research institutes and public health organisations around the world are trying to sequence many thousands of people in order to be build up an idea of the genomes of the populations of their countries," she said. Lal added that massive data sets are collected that are very complicated and contain many different related kinds of information. "...the size and richness of the data sets that we're now getting in this field makes it really essential to use machine learning and deep learning to analyze this data in order to answer complicated questions like, for example, how do we identify people who are more at risk of developing various diseases before they actually develop signs of those diseases," she said.

For the past few weeks, I've been engaged in an email exchange with my favourite anarcho-syndicalist Noam Chomsky. I reached out to him initially to ask whether recent developments in ANNs (artificial neural networks) had caused him to reconsider his famous linguistic theory Universal Grammar. Our conversation touched on the possible limitations of Deep Learning, how well ANNs really model biological brains and also meandered into more philosophical territory. I'm not going to quote Professor Chomsky directly in this article as our discussion was informal but I will attempt to summarise the key take-aways. Noam Chomsky is first and foremost a professor of linguistics (considered by many to be "the father of modern linguistics") but he is probably better known outside of academic circles as an activist, philosopher and historian.

Before we start, if you are reading this article, I am sure that we share similar interests and are/will be in similar industries. So let's connect via Linkedin! Please do not hesitate to send a contact request! If you have been trying to build machine learning models with high accuracy; but never tried Transfer Learning, this article will change your life. At least, it did mine!

Brain-computer interfaces (BCIs) use decoding algorithms to control prosthetic devices based on brain signals for restoration of lost function. Computer-brain interfaces (CBIs), on the other hand, use encoding algorithms to transform external sensory signals into neural stimulation patterns for restoring sensation or providing sensory feedback for closed-loop prosthetic control. In this article, we introduce brain co-processors, devices that combine decoding and encoding in a unified framework using artificial intelligence (AI) to supplement or augment brain function. Brain co-processors can be used for a range of applications, from inducing Hebbian plasticity for rehabilitation after brain injury to reanimating paralyzed limbs and enhancing memory. A key challenge is simultaneous multi-channel neural decoding and encoding for optimization of external behavioral or task-related goals. We describe a new framework for developing brain co-processors based on artificial neural networks, deep learning and reinforcement learning. These "neural co-processors" allow joint optimization of cost functions with the nervous system to achieve desired behaviors. By coupling artificial neural networks with their biological counterparts, neural co-processors offer a new way of restoring and augmenting the brain, as well as a new scientific tool for brain research. We conclude by discussing the potential applications and ethical implications of brain co-processors.

The hyponym-hypernym relation is an essential element in the semantic network. Identifying the hypernym from a definition is an important task in natural language processing and semantic analysis. While a public dictionary such as WordNet works for common words, its application in domain-specific scenarios is limited. Existing tools for hypernym extraction either rely on specific semantic patterns or focus on the word representation, which all demonstrate certain limitations. Here we propose a method by combining both the syntactic structure in definitions given by the word's part of speech, and the bidirectional gated recurrent unit network as the learning kernel. The output can be further tuned by including other features such as a word's centrality in the hypernym cooccurrence network. The method is tested in the corpus from Wikipedia featuring definition with high regularity, and the corpus from Stack-Overflow whose definition is usually irregular. It shows enhanced performance compared with other tools in both corpora.

One way to understand how the brain adapts to its environment is to view it as a type of generative pattern-creation model [20], one that is engaged in a never-ending process of self-correction, often without external teaching signals (or labels) [53]. Under this perspective, the brain is continuously making predictions about elements of its environment, a process that allows it to infer useful representations of the sensory data it receives [56] as well as to synthesize novel patterns, which could serve as the potential basis for long-term planning and imagination itself [12]. From the theoretical viewpoint of predictive processing, the brain could be likened to a hierarchical model whose levels are implemented by neurons (or clusters of neurons). If levels are likened to regions of the brain, the neurons at one level (region) attempt to predict the state of neurons at another level (region) and adjust/correct their local model synaptic parameters based on how different their predictions were from the observed signal. Furthermore, these neurons utilize various mechanisms to laterally stimulate/suppress each other [40] to facilitate contextual processing (such as grouping/segmenting visual components of objects in a scene).

Deep neural networks have shown significant promise in comprehending complex visual signals, delivering performance on par or even superior to that of human experts. However, these models often lack a mechanism for interpreting their predictions, and in some cases, particularly when the sample size is small, existing deep learning solutions tend to capture spurious correlations that compromise model generalizability on unseen inputs. In this work, we propose a contrastive causal representation learning strategy that leverages proactive interventions to identify causally-relevant image features, called Proactive Pseudo-Intervention (PPI). This approach is complemented with a causal salience map visualization module, i.e., Weight Back Propagation (WBP), that identifies important pixels in the raw input image, which greatly facilitates the interpretability of predictions. To validate its utility, our model is benchmarked extensively on both standard natural images and challenging medical image datasets. We show this new contrastive causal representation learning model consistently improves model performance relative to competing solutions, particularly for out-of-domain predictions or when dealing with data integration from heterogeneous sources. Further, our causal saliency maps are more succinct and meaningful relative to their non-causal counterparts.

We study incremental learning for semantic segmentation where when learning new classes we have no access to the labeled data of previous tasks. When incrementally learning new classes, deep neural networks suffer from catastrophic forgetting of previous learned knowledge. To address this problem, we propose to apply a self-training approach that leverages unlabeled data, which is used for rehearsal of previous knowledge. Additionally, conflict reduction is proposed to resolve the conflicts of pseudo labels generated from both the old and new models. We show that maximizing self-entropy can further improve results by smoothing the overconfident predictions. The experiments demonstrate state-of-the-art results: obtaining a relative gain of up to 114% on Pascal-VOC 2012 and 8.5% on the more challenging ADE20K compared to previous state-of-the-art methods.

Background: The inception of next generations sequencing technologies have exponentially increased the volume of biological sequence data. Protein sequences, being quoted as the `language of life', has been analyzed for a multitude of applications and inferences. Motivation: Owing to the rapid development of deep learning, in recent years there have been a number of breakthroughs in the domain of Natural Language Processing. Since these methods are capable of performing different tasks when trained with a sufficient amount of data, off-the-shelf models are used to perform various biological applications. In this study, we investigated the applicability of the popular Skip-gram model for protein sequence analysis and made an attempt to incorporate some biological insights into it. Results: We propose a novel $k$-mer embedding scheme, Align-gram, which is capable of mapping the similar $k$-mers close to each other in a vector space. Furthermore, we experiment with other sequence-based protein representations and observe that the embeddings derived from Align-gram aids modeling and training deep learning models better. Our experiments with a simple baseline LSTM model and a much complex CNN model of DeepGoPlus shows the potential of Align-gram in performing different types of deep learning applications for protein sequence analysis.