No abstract

Deep neural networks have demonstrated their superior performance in almost every Natural Language Processing task, however, their increasing complexity raises concerns. A particular concern is that these networks pose high requirements for computing hardware and training budgets. The state-of-the-art transformer models are a vivid example. Simplifying the computations performed by a network is one way of addressing the issue of the increasing complexity. In this paper, we propose an end to end binarized neural network for the task of intent and text classification. In order to fully utilize the potential of end to end binarization, both the input representations (vector embeddings of tokens statistics) and the classifier are binarized. We demonstrate the efficiency of such a network on the intent classification of short texts over three datasets and text classification with a larger dataset. On the considered datasets, the proposed network achieves comparable to the state-of-the-art results while utilizing ∼ 20-40% lesser memory and training time compared to the benchmarks.

Glioblastoma is an aggressive and reccurent tumour that affects our brain and spinal cord with an extensively poor prognosis and death of the patient within 14-15 months of diagnosis. The tumour originates from astrocytes and therefore comes under the glioma known as astrocytoma. These tumours exhibit miscellaneous properties and contain cancer stem cells (CSCs). The stem cells exhibit diverse mechanisms through which these cells indulge in the proliferation and renewal of their systems. CSCs pose a significant obstacle as far as cancer therapy is concerned, which incorporates blocking important signalling pathways involved in CSCs’ self-renewal and survival which may also include inhibition of the ATP-binding cassette transporters. Nanomedicine, biomarkers and drug delivery technology-based approaches using nanoparticles have tremendous ability to tackle the restrictions impending clinical applications, such as diagnosis and targeting of CSC-specific agents. Nanocarrier-based therapeutic agents have shown a potential of penetrating CSCs and increasing drug accumulation in CSCs. Nanomedicine can overcome ATP-driven pump-mediated multidrug resistance while also reducing the harmful effects on non-cancerous cells. The objective of this review is to examine advantages of nanomedicine and the innovative approaches that have been explored to address the challenges presented by CSCs in order to control the progression of glioblastomas by developing novel nanotherapeutic interventions which target CSCs.

No abstract

Deep neural networks have demonstrated their superior performance in almost every Natural Language Processing task, however, their increasing complexity raises concerns. In particular, these networks require high expenses on computational hardware and training budget is a concern for many. Even for a trained network, the inference phase can be too demanding for resourceconstrained devices, thus limiting its applicability. The state-of-the-art transformer models are a vivid example. Simplifying the computations performed by a network is one way of relaxing the complexity requirements. In this paper, we propose an end to end binarized neural network architecture for the intent classification task. In order to fully utilize the potential of end to end binarization, both input representations (vector embeddings of tokens statistics) and the classifier are binarized. We demonstrate the efficiency of such architecture on the intent classification of short texts over three datasets and for text classification with a larger dataset. The proposed architecture achieves comparable to the state-of-the-art results on standard intent classification datasets while utilizing ∼ 20-40% lesser memory and training time. Furthermore, the individual components of the architecture, such as binarized vector embeddings of documents or binarized classifiers, can be used separately with not necessarily fully binary architectures.